1053-5888/05/$20.00©2005IEEE IEEE SIGNAL PROCESSING MAGAZINE [81] SEPTEMBER 2005 (2008)
Nelson Morgan, Qifeng Zhu, Andreas Stolcke, Kemal Sönmez, Sunil Sivadas, Takahiro Shinozaki, ...
[Beyond the spectral envelope as the fundamental representation for speech recognition]
Daniel Jurafsky, Chuck Wooters, Jonathan Segal, Andreas Stolcke, Eric Fosler, Gary Tajchman, ...
This paper describes a number of experiments in adding new grammatical knowledge to the Berkeley Restaurant Project (BeRP), our medium-vocabulary (1300 word), speaker-independent, spontaneous...
Hynek Hermansky, Nelson Morgan, Senior Member
Abs#ract- Performance of even the best current stochastic short-term spectral representation of speech will be typically recognizers severely degrades in an unexpected communications severely...
Daniel Jurafsky, Chuck Wooters, Gary Tajchman, Jonathan Segal, Andreas Stolcke, Eric Fosler, ...
This paper describes the architecture and performance of the Berkeley Restaurant Project (BeRP), a medium-vocabulary, speaker-independent, spontaneous continuous speech understanding system currently...
Daniel Jurafsky, Chuck Wooters, Jonathan Segal, Andreas Stolcke, Eric Fosler, Gary Tajchman, ...
This paper describes a number of experiments in adding new grammatical knowledge to the Berkeley Restaurant Project (BeRP), our medium-vocabulary (1300 word), speaker-independent, spontaneous...
Modeling Consistency in a Speaker Independent Continuous Speech Recognition System (2008)
Yochai Konig, Nelson Morgan, Chuck Wooters, Victor Abrash, Michael Cohen, Horacio Franco
We would like to incorporate speaker-dependent consistencies, such as gender, in an otherwise speaker-independent speech recognition system. In this paper we discuss a Gender Dependent Neural Network...
Barry Y. Chen, Qifeng Zhu, Nelson Morgan
We have been reducing word error rates (WERs) on conversational telephone speech (CTS) tasks by capturing long-term (˜500ms) temporal information using multi-layered perceptrons (MLPs). In this...
Daniel Jurafsky, Chuck Wooters, Gary Tajchman, Jonathan Segal, Andreas Stolcke, Eric Fosler, ...
This paper describes the architecture and performance of the Berkeley Restaurant Project (BeRP), a medium-vocabulary, speaker-independent, spontaneous continuous speech understanding system currently...
Automatic Data Selection for MLP-based Feature Extraction for ASR (2008)
Carmen Peláez-moreno, Qifeng Zhu, Barry Chen, Nelson Morgan
The use of huge databases in ASR has become an important source of ASR system improvements in the last years. However, their use demands an increase of the computational resources necessary to train...
Krste Asanovic, Ras Bodik, James Demmel, Tony Keaveny, Kurt Keutzer, John D. Kubiatowicz, ...
Copyright © 2008, by the author(s). All rights reserved. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that...
Hybrid Neural Network/hidden Markov Model Continuous-Speech Recognition (2007)
Michael Cohen, Horacio Franco, Nelson Morgan, David Rumelhart, Victor Abrash
n M In this paper we present a hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recognib tion system, in which the advantages of both approaches are...
Integrating Neural Networks Into Computer Speech Recognition Systems (2007)
Michael Cohen, Horacio Franco, Nelson Morgan, David Rumelhart, Victor Abrash, Yochai Konig
this paper we describe the ini ial baseline DECIPHER system and the approach for n integrating MLP-based estimation techniques; present a umber of new techniques that have been developed to allow d l...
STOCHASTIC PERCEPTUAL SPEECH MODELS WITH DURATIONAL DEPENDENCE (2007)
Jeff Bilmes T, Nelson Morgan, Su-lin Wu, Herv Bourlard
In [6], we develop statisticaJ model of speech recognition where emphasis is placed on the pcrccptuaJly-rclcvant and information-rich portion of the speech signaJ. In that model, speech is viewed as...
Transition-Based Connectionist Speech Recognition (2007)
Yochai Konig, Herv Bourlard, Nelson Morgan
In this paper, we introduce REMAP, an approach for the training and estimation of posterior probabilities using a recurslye algorithm that is reminiscent of the EM-based Forward-Backward (Liporace...
Far-field ASR on Inexpensive Microphones (2007)
Laura Docio-fern, David Gelbart, Nelson Morgan
For a connected digits speech recognition task, we have compared the performance of two inexpensive electret microphones with that of a single high quality PZM microphone. Recognition error rates...
Nelson Morgan, Sangita Tibrewala
This is a summary of research conducted by the �Questionable Parameter Group " at the Johns Hopkins 1996 Summer Workshop. The focus in this group was on signal representation and acoustic...
Daniel Jurafsky, Chuck Wooters, Jonathan Segal, Andreas Stolcke, Gary Tajchman, Nelson Morgan
This paper describes a number of experiments in adding new grammatical knowledge to the Berkeley Restaurant Project (BeRP), our medium-vocabulary (1300 word), speaker-independent, spontaneous...
Daniel Jurafsky, Chuck Wooters, Jonathan Segal, Andreas Stolcke, Eric Fosler, Gary Tajchman, ...
This paper describes a number of experiments in adding new grammatical knowledge to the Berkeley Restaurant Project (BeRP), our medium-vocabulary (1300 word), speaker-independent, spontaneous...
Address correspondence to: (2007)
Michael Cohen, Nelson Morgan, David Rumelhart, Victor Abrash, Horacio Franco, Horacio Franco
In this paper we present a training method and a network architecture for estimating contextdependent observation probabilities in the framework of a hybrid hidden Markov model (HMM) / multi layer...
The Meeting Project at ICSI (2007)
Morgan, Nelson, Baron, Don, Edwards, Jane, Ellis, Dan, Gelbart, David, Janin, Adam, ...
In collaboration with colleagues at UW, OGI, IBM, and SRI, we are developing technology to process spoken language from informal meetings. The work includes a substantial data collection and...
Recent innovations in speech-to-text transcription at sri-icsi-uw (2006)
Andreas Stolcke, Senior Member, Barry Chen, Horacio Franco, Venkata Ramana Rao, Martin Graciarena, ...
Abstract — We summarize recent progress in automatic speechto-text
Recent innovations in speech-to-text transcription at sri-icsi-uw (2006)
Andreas Stolcke, Senior Member, Barry Chen, Horacio Franco, Venkata Ramana Rao, Martin Graciarena, ...
Abstract — We summarize recent progress in automatic speechto-text
Improved MLP structures for data-driven feature extraction for ASR (2005)
Qifeng Zhu, Barry Chen, Frantisek Grezl, Nelson Morgan
In this paper, we present our recent progress on multi-layer perceptron (MLP) based data-driven feature extraction using improved MLP structures. Four-layer MLPs are used in this study. Different...
Using MLP features in SRI’s conversational speech recognition system (2005)
Qifeng Zhu, Andreas Stolcke, Barry Y. Chen, Nelson Morgan
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLP). The acoustic...
Using MLP features in SRI’s conversational speech recognition system (2005)
Qifeng Zhu, Andreas Stolcke, Barry Y. Chen, Nelson Morgan
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLP). The acoustic...
Towards Using Hierarchical Posteriors for Flexible Automatic Speech Recognition Systems (2004)
Bourlard, Hervé, Bengio, Samy, Doss, Mathew Magimai, Zhu, Qifeng, Mesot, Bertrand, Morgan, Nelson
Local state (or phone) posterior probabilities are often investigated as local classifiers (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., ``Tandem'') towards improved...
Towards using hierarchical posteriors for flexible automatic speech recognition systems (2004)
Bourlard, Hervé, Bengio, Samy, Doss, Mathew Magimai, Zhu, Qifeng, Mesot, Bertrand, Morgan, Nelson
Local state (or phone) posterior probabilities are often investigated as local classifiers (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., ``Tandem'') towards improved...
Nelson Morgan, Barry Y. Chen, Qifeng Zhu, Andreas Stolcke
TempoRAl Patterns (TRAPs) and Tandem MLP/HMM approaches incorporate feature streams computed from longer time intervals than the conventional short-time analysis. These methods have been used for...
On Using MLP Features in LVCSR (2004)
Qifeng Zhu Barry, Barry Chen, Nelson Morgan, Andreas Stolcke
One of the major research thrusts in the speech group at ICSI is to use Multi-Layer Perceptron (MLP) based features in automatic speech recognition (ASR). This paper presents a study of three aspects...
The ICSI Meeting Project: Resources and Research (2004)
Adam Janin, Jeremy Ang, Sonali Bhagat, Rajdip Dhillon, Jane Edwards, Javier Macías-guarasa, ...
This paper provides a progress report on ICSI’s Meeting Project, including both the data collected and annotated as part of the project, as well as the research lines such materials support. We...
Learning long-term temporal features in LVCSR using neural networks (2004)
Barry Chen, Qifeng Zhu, Nelson Morgan
Incorporating long-term (500-1000 ms) temporal information using multi-layered perceptrons (MLPs) has improved performance on ASR tasks, especially when used to complement traditional short-term...
Nelson Morgan, Barry Y. Chen, Qifeng Zhu, Andreas Stolcke
TempoRAl Patterns (TRAPs) and Tandem MLP/HMM approaches incorporate feature streams computed from longer time intervals than the conventional short-time analysis. These methods have been used for...
Scaling up: Learning large-scale recognition methods from smallscale recognition tasks (2004)
Nelson Morgan, Barry Y Chen, Qifeng Zhu, Andreas Stolcke
Despite the common wisdom that lessons learned from small experimental speech recognition tasks often do not scale to larger tasks, many important algorithms used in larger tasks were first developed...
Incorporating tandem/HATs MLP features into SRI’s conversational speech recognition system (2004)
Qifeng Zhu, Andreas Stolcke, Barry Y. Chen, Nelson Morgan
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLPs). The acoustic...
Hermansky, Hynek, Morgan, Nelson
What is a Negative Result? In a sense, well-designed experiments never have a completely negative result, since there is always the opportunity to learn something. In fact, unexpected results by...
Meetings about meetings: research at ICSI on speech in multiparty conversations (2003)
Nelson Morgan, Don Baron, Sonali Bhagat, David Gelbart, Adam Janin
In early 2001 we reported (at the Human Language Technology meeting) the early stages of an ICSI project on processing speech from meetings (in collaboration with other sites, principally SRI,...
The ICSI meeting corpus (2003)
Adam Janin, Don Baron, Jane Edwards, Dan Ellis, David Gelbart, Nelson Morgan, ...
We have collected a corpus of data from natural meetings that occurred at the International Computer Science Institute (ICSI) in Berkeley, California over the last three years. The corpus contains...
Qualcomm-ICSI-OGI features for ASR (2002)
Andre Adami, Lukas Burget, Stephane Dupont, Hari Garudadri, Frantisek Grezl, Hynek Hermansky, ...
Our feature extraction module for the Aurora task is based on a combination of a conventional noise supression technique (Wiener filtering) with our temporal processing technigues (linear...
Far-field microphone speech signals cause high error rates for automatic speech recognition systems, due to room reverberation and lower signal-to-noise ratios. We have observed large increases in...
Far-field microphone speech signals cause high error rates for automatic speech recognition systems, due to room reverberation and lower signal-to-noise ratios. We have observed large increases in...
The meeting project at ICSI (2001)
Nelson Morgan, Don Baron, Jane Edwards, Dan Ellis, David Gelbart, Adam Janin, ...
Evaluating Long-term Spectral Subtraction for Reverberant ASR (2001)
Even a modest degree of room reverberation can greatly increase the difficulty of Automatic Speech Recognition. We have observed large increases in speech recognition word error rates when using a...
The meeting project at ICSI (2001)
Nelson Morgan, Don Baron, Jane Edwards, Dan Ellis, David Gelbart, Adam Janin, ...
In collaboration with colleagues at UW, OGI, IBM, and SRI, we are developing technology to process spoken language from informal meetings. The work includes a substantial data collection and...
Automatic Speech Recognition (2001)
Martigny Valais Suisse, Franoise Beaufays, Nelson Morgan
internet
The meeting project at ICSI (2001)
Nelson Morgan, Don Baron, Jane Edwards, Dan Ellis, David Gelbart, Adam Janin, ...
Evaluating Long-term Spectral Subtraction for Reverberant ASR (2001)
Even a modest degree of room reverberation can greatly increase the difficulty of Automatic Speech Recognition. We have observed large increases in speech recognition word error rates when using a...
Automatic Labeling of Semantic Roles (2000)
Daniel Gildea, Nelson Morgan, Jerome Feldman Eecs
The problem of linking syntactic constituents of a sentence to semantic roles is an essential part of many natural language processing tasks. The research outlined here aims to develop a statistical...
An Overview of the SPRACH System for the Transcription of Broadcast News (1999)
Cook, Gary, Christie, James, Ellis, Dan, Fosler-Lussier, Eric, Gotoh, Yoshihiko, Kingsbury, Brian, ...
This paper describes the SPRACH system developed for the 1998 Hub-4E broadcast news evaluation. The system is based on the connectionist-HMM framework and uses both recurrent neural network and...
An Overview of the SPRACH System for the Transcription of Broadcast News (1999)
Cook, Gary, Christie, James, Ellis, Dan, Fosler-Lussier, Eric, Gotoh, Yoshihiko, Kingsbury, Brian, ...
This paper describes the SPRACH system developed for the 1998 Hub-4E broadcast news evaluation. The system is based on the connectionist-HMM framework and uses both recurrent neural network and...
Multi-stream speech recognition: Ready for prime time (1999)
Adam Janin, Dan Ellis, Nelson Morgan
Multi-stream and multi-band methods can improve the accuracy of speech recognition systems without overly increasing the complexity. However, they cannot be applied blindly. In this paper, we review...
Combined speech and speaker recognition with speaker-adapted connectionist models (1999)
Dominique Genoud, Dan Ellis, Nelson Morgan
One approach to speaker adaptation for the neural-network acoustic models of a hybrid connectionist-HMM speech recognizer is to adapt a speaker-independent network by performing a small amount of...
Simultaneous Speech and Speaker Recognition Using Hybrid Architecture (1999)
Dominique Genoud, Dan Ellis, Nelson Morgan
This rapport summarize the workthatwas done this last 6 month at ICSI in speaker recognition and speaker adaptation. 1 Introduction The automatic recognition process of the human voice is often...
Combined Speech And Speaker Recognition With Speaker-Adapted Connectionist Models (1999)
Dominique Genoud, Dan Ellis, Nelson Morgan
One approach to speaker adaptation for the neural-network acoustic models of a hybrid connectionist-HMM speech recognizer is to adapt a speaker-independent network by performing a small amount of...
Effects Of Speaking Rate And Word Frequency On Conversational Pronunciations (1999)
Eric Fosler-lussier, Nelson Morgan
The possible set of pronunciations in continuous speech corpora change dynamically with many factors. Two variables, speaking rate and word predictability, seemed to be promising candidates for...
Incorporating Contextual Phonetics Into Automatic Speech Recognition (1999)
Steven Greenberg, Nelson Morgan
This work outlines the problems encountered in modeling pronunciation for automatic speech recognition (ASR) of spontaneous (American) English speech. We detail some of the phonetic phenomena within...
Sooner Or Later: Exploring Asynchrony In Multi-Band Speech Recognition (1999)
Nikki Mirghafori, Nelson Morgan
Multi-band speech recognition is an exploratory paradigm in which each frequency region is treated as a distinct source of information and the streams are combined after each is processed...
Multi-Stream Speech Recognition: Ready For Prime Time? (1999)
Adam Janin, Dan Ellis, Nelson Morgan
Multi-stream and multi-band methods can improve the accuracy of speech recognition systems without overly increasing the complexity. However, they cannot be applied blindly. In this paper, we review...
An Overview of the SPRACH System for the Transcription of Broadcast News (1999)
Gary Cook, James Christie, Dan Ellis, Eric Fosler-lussier, Yoshi Gotoh, Brian Kingsbury, ...
This paper describes the SPRACH system developed for the 1998 Hub-4E broadcast news evaluation. The system is based on the connectionist-HMM framework and uses both recurrent neural network and...
Sprach System For, Gary Cook, James Christie, Dan Ellis, Eric Fosler-lussier, Yoshi Gotoh, ...
This paper describes the SPRACH system developed for the 1998 Hub-4E broadcast news evaluation. The system is based on the connectionist-HMM framework and uses both recurrent neural network and...
Sprach System For, Gary Cook, James Christie, Dan Ellis, Eric Fosler-lussier, Yoshi Gotoh, ...
This paper describes the SPRACH system developed for the 1998 Hub-4E broadcast news evaluation. The system is based on the connectionist-HMM framework and uses both recurrent neural network and...
Incorporating Contextual Phonetics Into Automatic Speech Recognition (1999)
Eric Fosler-Lussier, Steven Greenberg, Nelson Morgan, Stevengreenberg Y, Nelson Morgan ?y
This work outlines the problems encountered in modeling pronunciation for automatic speech recognition (ASR) of spontaneous (American) English speech. We detail some of the phonetic phenomena within...
1997 IEEE Workshop on Neural Networks for Signal Processing VII (1998)
Principe, Jose, Gile, Lee, Morgan, Nelson, Wilson, Elizabeth
NNSP'07 was held In Amelia Island Plantation, Amelia Island Florida, September 24-26, 1997. NNSP'97 was sponsored by the Neural Networks Technical Committee of the IEEE Signal Processing Society, in...
Neural Networks for Signal Processing VII Proceeding of the 1997 IEEE Workshop (1998)
Principe, Jose, Gile, Lee, Morgan, Nelson, Wilson, Elizabeth
This year topics were blind signal processing and pattern recognition applications. The highlights of the conference were the following: (1) the advances made on blind source separation, both at the...
Combining multiple estimators of speaking rate (1998)
Nelson Morgan, Eric Fosler-lussier
We report progress in the development of a measure of speaking rate that is computed from the acoustic signal. The newest form of our analysis incorporates multiple estimates of rate; besides the...
Incorporating information from syllable-length time scales into automatic speech recognition (1998)
Su-lin Wu, Nelson Morgan, Steven Greenberg
Including information distributed over intervals of syllabic duration (100–250 ms) may greatly improve the performance of automatic speech recognition (ASR) systems. ASR systems primarily use...
Combining multiple estimators of speaking rate (1998)
Nelson Morgan, Eric Fosler-lussier
We report progress in the development of a measure of speaking rate that is computed from the acoustic signal. The newest form of our analysis incorporates multiple estimates of rate; besides the...
Su-lin Wu, Nelson Morgan, Steven Greenberg
Combining knowledge derived from both syllable- (100-250 ms) and phone-length (40-100 ms) intervals in the automatic speech recognition process can yield performance superior to that obtained using...
Combining Multiple Estimators of Speaking Rate (1998)
Nelson Morgan, Eric Fosler-lussier
We report progress in the development of a measure of speaking rate that is computed from the acoustic signal. The newest form of our analysis incorporates multiple estimates of rate; besides the...
Speaker Verification - A Quick Overview (1998)
A Quick Overview, Hervé Bourlard, Nelson Morgan
ignal Processing in Humans and Machines (publisher still to be defined), by Ben Gold and Nelson Morgan. 2 IDIAP--RR 98-12 1 Introduction Speech contains many characteristics that are specific to each...
Incorporating Information From Syllable-Length Time Scales Into Automatic Speech Recognition (1998)
Su-lin Wu, Nelson Morgan, Steven Greenberg
Including information distributed over intervals of syllabic duration (100--250 ms) may greatly improve the performance of automatic speech recognition (ASR) systems. ASR systems primarily use...
Hybrid HMM/ANN Systems for Speech Recognition: Overview and New Research Directions (1998)
this paper, we first give a brief overview of current state-of-the-art Automatic Speech Recognition (ASR), and then describe the use of ANNs as statistical estimators. We then review the basic...
A Supercomputer for Neural Computation, (1997)
Asanovic, Krste, Beck, James, Feldman, Jerome, Morgan, Nelson, Wawrzynek, John
The requirement to train large neural networks quickly has prompted the design of a new massively parallel supercomputer using custom VLSI. This design features 128 processing nodes, communicating...
Accelerator Systems for Neural Networks, Speech, and Related Applications. (1997)
Morgan, Nelson, Feldman, Jerome, Wawrzynek, John
During the contract period the contractor: (1) Explored the requirements for two new applications in order to improve the capabilities for CNS-1 computation beyond the speech tasks that we have...
A Study of Computational Requirements for Problems in Pattern Recognition. (1997)
Morgan, Nelson, Feldman, Jerome
During the contract period we: (1) Considered connectionist computation, particularly asit has been used for applications in speech recognition, and developed perspectives on machine requiremebts for...
Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems. (1997)
Hennebert, J, Ris, C, Bourlard, Herve, Renals, Steve, Morgan, Nelson
The results of our research presented in this paper are two-fold. First, an estimation of global posteriors is formalized in the framework of hybrid HMM/ANN systems. It is shown that hybrid HMM/ANN...
Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems. (1997)
Hennebert, J, Ris, C, Bourlard, H, Renals, Steve, Morgan, Nelson
The results of our research presented in this paper are two-fold. First, an estimation of global posteriors is formalized in the framework of hybrid HMM/ANN systems. It is shown that hybrid HMM/ANN...
Integrating syllable boundary information into speech recognition (1997)
Su-lin Wu, Michael L. Shire, Steven Greenberg, Nelson Morgan
In this paper we examine the proposition that knowledge of the timing of syllabic onsets may be useful in improving the performance of speech recognition systems. A method of estimating the location...
Transmissions and transitions: A study of two common assumptions in multi-band ASR (1997)
Nikki Mirghafori, Nelson Morgan
Is multi-band ASR inherently inferior to a full-band approach because phonetic information is lost due to the division of the frequency space into sub-bands? Do the phonetic transitions in sub-bands...
Integrating Syllable Boundary Information Into Speech Recognition (1997)
Su-lin Wu, Michael L. Shire, Steven Greenberg, Nelson Morgan
In this paper we examine the proposition that knowledge of the timing of syllabic onsets may be useful in improving the performance of speech recognition systems. A method of estimating the location...
Improving Asr Performance For Reverberant Speech (1997)
Brian Kingsbury, Nelson Morgan, Steven Greenberg
The performance of current automatic speech recognition (ASR) systems is very sensitive to the presence of room reverberation in the incoming speech signal. We investigate a family of front-end...
Integrating Syllable Boundary Information Into Speech Recognition (1997)
Su-lin Wu, Michael L. Shire, Steven Greenberg, Nelson Morgan
In this paper we examine the proposition that knowledge of the timing of syllabic onsets may be useful in improving the performance of speech recognition systems. A method of estimating the location...
Robust Features And Environmental Compensation: A Few Comments (1997)
ble emphasis on exploiting a range of solutions to linear disturbances, including both modelbased and feature-based compensations. When information about the nature of the disturbance (or about the...
Improving ASR Performance For Reverberant Speech (1997)
Nelson Morgan, Steven Greenberg
The performance of current automatic speech recognition (ASR) systems is very sensitive to the presence of room reverberation in the incoming speech signal. We investigate a family of front-end...
Recognizing Reverberant Speech With Rasta-Plp (1997)
The performance of the PLP, log-RASTA-PLP, and J-RASTA-PLP front ends for recognition of highly reverberant speech is measured and compared with the performance of humans and the performance of an...
Speech Recognition Using On-Line Estimation Of Speaking Rate (1997)
Nelson Morgan, Eric Fosler, Nikki Mirghafori
In this paper, we describe a rate of speech estimator that is derived directly from the acoustic signal. This measure has been developed as an alternative to lexical measures of speaking rate such as...
Stochastic Perceptual Speech Models With Durational Dependence (1996)
Je Bilmes, Nelson Morgan, Su-lin Wu
In �6�, we develop statistical model of speech recognition where emphasis is placed on the perceptually-relevant and information-rich portion of the speech signal. In that model, speech is viewed...
Towards robustness to fast speech in ASR (1996)
Nikki Mirghafori, Eric Fosler, Nelson Morgan
Psychoacoustic studies show that human listeners are sen-sitive to speaking rate variations [t0]. Automatic speech recognition (ASR) systems are even more affected by the changes in rate, as double...
Spert-II: A Vector Microprocessor System (1996)
John Wawrzynek, Krste Asanovic, Brian Kingsbury, David Johnson, James Beck, Nelson Morgan
this article. Primary support for our work came from ONR URI Grant N00014-92-J-1617, ARPA Contract N0001493-C0249, NSF Grant MIP-9311980, and NSF PYI AwardMIP-8958568NSF.Additional support was...
John Wawrzynek, Brian Kingsbury, James Beck, David Johnson, Nelson Morgan
We report on our development of a high-performance system for neural network and other signal processing applications. We have designed and implemented a vector microprocessor and packaged it as an...
Remap - Experiments With Speech Recognition (1996)
Yochai Konig, Hervé Bourlard, Nelson Morgan
In this report we present experimental and theoretical results using a framework for training and modeling continuous speech recognition systems based on the theoretically optimal Maximum a...
Stochastic Perceptual Speech Models with Durational Dependence (1996)
Jeff Bilmes, Nelson Morgan, Su-lin Wu, Hervé Bourlard
In [6], we develop statistical model of speech recognition where emphasis is placed on the perceptually-relevant and information-rich portion of the speech signal. In that model, speech is viewed as...
Towards Robustness To Fast Speech In ASR (1996)
Nikki Mirghafori, Eric Fosler, Nelson Morgan
Psychoacoustic studies show that human listeners are sensitive to speaking rate variations [10]. Automatic speech recognition (ASR) systems are even more affected by the changes in rate, as double to...
Stochastic Perceptual Speech Models With Durational Dependence (1996)
Je Bilmes, Nelson Morgan, Su-lin Wu, Herve Bourlard
In [6], we develop statistical model of speech recognition where emphasis is placed on the perceptually-relevant and information-rich portion of the speech signal. In that model, speech is viewed as...
Stochastic Perceptual Models of Speech (1995)
Nelson Morgan, Hervd Bourlard, Steven Greenberg, Hynek Hermansky, Su-lin Wu
We have recently developed a statistical model of speech that avoids a number of current constraining assumptions for statistical speech recognition systems, particularly the model of speech as a...
Transition-based statistical training for ASR (1995)
Nelson Morgan, Yochai Konig, Su-lin Wu, Hervd Bourlard
It is known that in human speech recognition, the perceptually-dominant and information-rich portions of the speech signal, which may also be the parts with a better
The challenge of spoken language systems: Research directions for the nineties (1995)
Ron Cole, Lynette Hirschman, Les Atlas, Hynek Hermansky, Patti Price, ...
Footnote This article is based on a February, 1992workshop sponsored by the National Science
Transition-Based Statistical Training for ASR (1995)
Nelson Morgan, Hervé Bourlard, Yochai Konig, Su-lin Wu
INTRODUCTION It is known that in human speech recognition, the perceptually -dominant and information-rich portions of the speech signal, which may also be the parts with a better chance to withstand...
Stochastic Perceptual Models Of Speech (1995)
Nelson Morgan, Hervé Bourlard, Steven Greenberg, Hynek Hermansky, Su-lin Wu
Wehave recently developed a statistical model of speech that avoids a number of current constraining assumptions for statistical speech recognition systems, particularly the model of speech as a...
The Challenge of Spoken Language Systems: Research Directions for the Nineties (1995)
Ron Cole, Lynette Hirschman, Les Atlas, Hynek Hermansky, Patti Price, ...
This article is based on a February, 1992 workshop sponsored by the National Science Foundation entitled "Workshop on Spoken Language Understanding." The Workshop was supported by Grant No....
Why Is Asr Harder For Fast Speech And What Can We Do About It? (1995)
Nikki Mirghafori, Eric Fosler, Nelson Morgan
INTRODUCTION It has been observed in various NIST evaluations (e.g. WSJ-Nov93 & RM-Sep92) that ASR systems typically have about 2-3 times higher word error rates on very fast speakers [2, 3]....
Fast Speakers In Large Vocabulary Continuous Speech Recognition: Analysis Antidotes (1995)
Nikki Mirghafori, Eric Fosler, Nelson Morgan
The performance of automatic speech recognizers (ASR) typically degrades for test speakers with "outlier" characteristics, for example, speakers with foreign accent and fast speaking rate....
Hervé Bourlard, Yochai Konig, Nelson Morgan
In this paper, we briefly describe REMAP, an approach for the training and estimation of posterior probabilities, and report its application to speech recognition. REMAP is a recursive algorithm that...
Using A Stochastic Context-Free Grammar As A Language Model For Speech Recognition (1995)
Daniel Jurafsky, Chuck Wooters, Jonathan Segal, Andreas Stolcke, Eric Fosler, Gary Tajchman, ...
This paper describes a number of experiments in adding new grammatical knowledge to the Berkeley Restaurant Project (BeRP), our medium-vocabulary (1300 word), speaker-independent, spontaneous...
Stochastic Perceptual Models of Speech (1995)
Nelson Morgan, Hervé Bourlard, Steven Greenberg, Hynek Hermansky, Su-lin Wu
We have recently developed a statistical model of speech that avoids a number of current constraining assumptions for statistical speech recognition systems, particularly the model of speech as a...
Yochai Konig, Hervé Bourlard, Nelson Morgan
In this paper, we introduce REMAP, an approach for the training and estimation of posterior probabilities using a recursive algorithm that is reminiscent of the EM-based Forward-Backward (Liporace...
Digit Recognition With Stochastic Perceptual Speech Models (1995)
Nelson Morgan, Su-lin Wu, Hervé Bourlard
We have recently developed a statistical model of speech that focuses statistical modeling power on phonetic transitions. These are the perceptually-dominant and informationrich portions of the...
The Challenge of Spoken Language Systems: Research Directions for the Nineties (1995)
Ron Cole, Lynette Hirschman, Les Atlas, Hynek Hermansky, Patti Price, ...
A spoken language system combines speech recognition, natural language processing and human interface technology. It functions by recognizing the person's words, interpreting the sequence of...
Connectionist probability estimators in HMM speech recognition (1994)
Renals, Steve, Morgan, Nelson, Bourlard, Herve, Cohen, Michael, Franco, Horacio
The authors are concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system. This is achieved through a statistical interpretation of connectionist...
Connectionist probability estimators in HMM speech recognition (1994)
Renals, Steve, Morgan, Nelson, Bourlard, Herve, Cohen, Michael, Franco, Horacio
The authors are concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system. This is achieved through a statistical interpretation of connectionist...
Connectionist Probability Estimators in HMM Speech Recognition (1994)
Steve Renals, Nelson Morgan, Senior Member, Hervc Bourlard, Michael Cohen, Horacio Franco
Abstract- We are concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system. This is achieved through a statistical interpretation of connectionist...
Connectionist Probability Estimators in HMM Speech Recognition (1994)
Steve Renals, Nelson Morgan, Hervé Bourlard, Michael Cohen, Horacio Franco
Abstract—We are concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system. This is achieved through a statistical interpretation of connectionist...
Connectionist Probability Estimators in HMM Speech Recognition (1994)
This report is concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system, This is achieved through a statistical understanding of connectionist...
A supercomputer for neural computation (1994)
Krste Asanovic, James Beck, Jerome Feldman, Nelson Morgan, John Wawrzynek
Abstract | The requirement to train large neural networks quickly has prompted the design of a new massively parallel supercomputer using custom VLSI. This design features 128 processing nodes,...
Connectionist Probability Estimators in HMM Speech Recognition (1994)
This report is concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system, This is achieved through a statistical understanding of connectionist...
Stochastic Perceptual Auditory-Event-Based Models For Speech Recognition (1994)
Nelson Morgan Herv'e, Nelson Morgan, Steven Greenberg, Hynek Hermansky
We have developed a statistical model of speech that incorporates certain temporal properties of human speech perception. The primary goal of this work is to avoid a number of current constraining...
Modeling Dynamics In Connectionist Speech Recognition - The Time Index Model (1994)
We are experimenting with an approach to connectionist speech recognition that models the dynamics within a speech segment using temporal position as an explicit variable. Currently, the most common...
Daniel Jurafsky, Chuck Wooters, Gary Tajchman, Jonathan Segal, Andreas Stolcke, Nelson Morgan
This paper describes three preliminary experiments in adding new language knowledge to the recognizer BeRP:
A Supercomputer for Neural Computation (1994)
Krste Asanovic, James Beck, Jerome Feldman, Nelson Morgan, John Wawrzynek
The requirement to train large neural networks quickly has prompted the design of a new massively parallel supercomputer using custom VLSI. This design features 128 processing nodes, communicating...
Connectionist Probability Estimators in HMM Speech Recognition (1994)
Steve Renals, Nelson Morgan, Hervé Bourlard, Michael Cohen, Horacio Franco
We are concerned with integrating connectionist networks into a hidden Markovmodel (HMM) speech recognition system. This is achieved through a statistical interpretation of connectionist networks as...
The Berkeley Restaurant Project (1994)
Daniel Jurafsky, Chuck Wooters, Gary Tajchman, Jonathan Segal, Andreas Stolcke, Eric Fosler, ...
This paper describes the architecture and performance of the Berkeley Restaurant Project (BeRP), a medium-vocabulary, speaker-independent, spontaneous continuous speech understanding system currently...
Daniel Jurafsky, Chuck Wooters, Jonathan Segal, Andreas Stolcke, Nelson Morgan
As the field of speech understanding matures, and particularly as the quality of front-end and phonetic components improves, researchers have begun to explore ways to add new kinds of language...
Connectionist Probability Estimators in HMM Speech Recognition (1994)
This report is concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system, This is achieved through a statistical understanding of connectionist...
Modeling dynamics in connectionist speech recognition - the time index model (1994)
emitted in a given speech unit (a “segment”), as opposed to a single acoustic vector as used for HMMs. The production of the acoustic We are experimenting with an approach to connectionist speech...
CNS-1 Architecture Specification - A Connectionist Network Supercomputer (1993)
Krste Asanovic, James Beck, Tim Callahan, Jerry Feldman, Brian Kingsbury, ...
This report proposes a massively parallel computer, the Connectionist Network Supercomputer(CNS-1), which leverages off these fields. By targeting the computer to connectionist networks and related...
The Design of a Neuro-Microprocessor (1993)
This paper presents the architecture of a neuro-microprocessor. This processor was designed using the results of careful analysis of our set of applications and extensive simulation of...
Designing a Connectionist Network Supercomputer (1993)
Krste Asanovic, James Beck, Jerry Feldman, Nelson Morgan, John Wawrzynek
This paper describes an effort at UC Berkeley and the International Computer Science Institute to develop a super-computer for artificial neural network applications. Our perspective has been...
The design of a neuro-microprocessor (1993)
John Wawrzynek, Krste Asanovic, Nelson Morgan, Senior Member
Abstract- This paper presents the architecture of a neuro-microprocessor. This processor was designed using the results of careful analysis of our set of applications and extensive simulation of...
CNS-1 Architecture Specification A Connectionist Network Supercomputer (1993)
Krste Asanović, James Beck, Tim Callahan, Jerry Feldman, Brian Kingsbury, ...
In the past two decades, the fields of VLSI systems design and massively parallel computation have grown into mature disciplines. Both fields began as research topics in industrial and academic...
Improving statistical speech recognition (1992)
Renals, Steve, Morgan, Nelson, Cohen, Michael, Franco, Horacio, Bourlard, Herve
A summary of the theory of the hybrid connectionist HMM (hidden Markov model) continuous speech recognition system is presented. Experimental results indicating that the connectionist methods can...
Improving statistical speech recognition (1992)
Renals, Steve, Morgan, Nelson, Cohen, Michael, Franco, Horacio, Bourlard, Herve
A summary of the theory of the hybrid connectionist HMM (hidden Markov model) continuous speech recognition system is presented. Experimental results indicating that the connectionist methods can...
CDNN: a context dependent neural network for continuous speech recognition (1992)
Bourlard, Herve, Morgan, Nelson, Wooters, Chuck, Renals, Steve
A series of theoretical and experimental results have suggested that multilayer perceptrons (MLPs) are an effective family of algorithms for the smooth estimate of highly dimensioned probability...
Connectionist probability estimation in the DECIPHER speech recognition system (1992)
Renals, Steve, Morgan, Nelson, Cohen, Michael, Franco, Horacio
The authors have previously demonstrated that feedforward networks can be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems (Renals et al., 1991)....
CDNN: a context dependent neural network for continuous speech recognition (1992)
Bourlard, Herve, Morgan, Nelson, Wooters, Chuck, Renals, Steve
A series of theoretical and experimental results have suggested that multilayer perceptrons (MLPs) are an effective family of algorithms for the smooth estimate of highly dimensioned probability...
Connectionist probability estimation in the DECIPHER speech recognition system (1992)
Renals, Steve, Morgan, Nelson, Cohen, Michael, Franco, Horacio
The authors have previously demonstrated that feedforward networks can be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems (Renals et al., 1991)....
Factoring Networks By A Statistical Method (1992)
INTRODUCTION Both on theoretical and practical grounds, it is generally preferable to reduce the number of parameters for a trainable classifier system. In particular, it would be desirable to factor...
Neurocomputing on the RAP (1992)
Nelson Morgan, Nelson Morgan, James Beck, James Beck, Phil Kohn, Phil Kohn, ...
In 1989 we designed and implemented a Ring Array Processor (RAP) for fast execution of our continuous speech recognition training algorithms, which have been dominated by connectionist calculations....
Connectionist Probability Estimation In The Decipher Speech Recognition System (1992)
Steve Renals Nelson, Nelson Morgan, Michael Cohen, Horacio Franco
Previously, we have demonstrated that feed-forward networks may be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems. Here these connectionist...
GDNN: A Gender-Dependent Neural Network for Continuous Speech Recognition (1992)
Yochai Konig, Nelson Morgan, Claudia Chandra
Conventional speaker-independent speech recognition systems do not consider speakerdependent parameters in the probability estimation of phonemes. These recognition systems are instead tuned to the...
Ron Cole, Lynette Hirschman, Les Atlas, Hynek Hermansky, Patti Price, ...
This report describes the key research topics, the expected benefits of the research, and recommendations to NSF on the infrastructure needed to support the research.
SPERT: A VLIW/SIMD Microprocessor for Artificial Neural Network Computations (1992)
Krste Asanovic, James Beck, Phil Kohn, Nelson Morgan, John Wawrzynek
SPERT (Synthetic PERceptron Testbed) is a fully programmable single chip microprocessor designed for efficient execution of artificial neural network algorithms. The first implementation will be in a...
Victor Abrash, Horacio Franco, Michael Cohen, Nelson Morgan, Yochai Konig
a s An approach to modeling long-term consistencies in peech signal within the framework of a hybrid Hidden ) s Markov Model (HMM) / Multilayer Perceptron (MLP peaker-independent continuous-speech...
Development of a Connectionist Network Supercomputer (1992)
Krste Asanovic, James Beck, Jerry Feldman, Nelson Morgan, John Wawrzynek
This paper describes an effort at UC Berkeley and the International Computer Science Institute to develop a super-computer for artificial neural network applications. We describe our applications...
Connectionist Probability Estimation in HMM Speech Recognition (1992)
This report is concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system, This is achieved through a statistical understanding of connectionist...
Combining Neural Networks And Hidden Markov Models For Continuous Speech Recognition (1992)
Michael Cohen, Ichael Cohen, David Rumelhart, Nelson Morgan, Horacio Franco, Victor Abrash, ...
e present a speaker-independent, continuous-speech recog- ( nition system based on a hybrid multilayer perceptron MLP)/hidden Markov model (HMM). The system come bines the advantages of both...
Connectionist Probability Estimation In The Decipher Speech Recognition System (1992)
Steve Renals, Nelson Morgan, Michael Cohen, Horacio Franco
Previously, we have demonstrated that feed-forward networks may be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems. Here these connectionist...
HiPNeT-1: A Highly Pipelined Architecture for Neural Network Training (1991)
Krste Asanovic, Nelson Morgan, John Wawrzynek
Current artificial neural network (ANN) algorithms require extensive computational resources. However, they exhibit massive fine-grained parallelism and require only moderate arithmetic precision....
The impact of reduced weight and output precision on the back-propagation training algorithm [Wer74, RHW86] is experimentally determined for a feed-forward multilayer perceptron. In contrast with...
Simulation of Reduced Precision Arithmetic for Digital Neural Networks Using the RAP Machine (1991)
Krste Asanovic, Nelson Morgan, John Wawrzynek
This paper describes some of our recent work in the development of computer architectures for efficient execution of artificial neural network algorithms. Our earlier system, the Ring Array Processor...
Probability Estimation By Feed-Forward Networks In Continuous Speech Recognition (1991)
We review the use of feed-forward networks as estimators of probability densities in hidden Markov modelling. In this paper we are mostly concerned with radial basis functions (RBF) networks. We note...
Probability Estimation By Feed-Forward Networks In Continuous Speech Recognition (1991)
Steve Renals, Nelson Morgan, Herv E Bourlard
: We review the use of feed-forward networks as estimators of probability densities in hidden Markov modelling. In this paper we are mostly concerned with radial basis functions (RBF) networks. We...
Connectionist Speech Recognition: Status and Prospects (1991)
Steve Renals, Nelson Morgan, Herve Bourlard, Michael Cohen, Horacio Franco, Chuck Wooters, ...
We report on recent advances in the ICSI connectionist speech recognition project. Highlights include: . Experimental results showing that connectionist methods can improve the performance of a...
Rasta-Plp Speech Analysis (1991)
Hynek Hermansky, Nelson Morgan, Aruna Bayya, Phil Kohn
Most speech parameter estimation techniques are easily influenced by the frequency response of the communication channel. We have developed a technique that is more robust to such steady-state...
The Ring Array Processor (RAP): Algorithms and Architecture (1990)
In our speech recognition research, we have been experimenting with layered "neural" algorithms as probabilistic estimators for a Hidden Markov Model (HMM) procedure [1]-[3]....
Talking chips / Nelson Morgan with special contributions from Jake Buurman and Lloyd Rice (1984)
Morgan, Nelson, Buurma, Jake, Rice, Lloyd, Benjamin, Beatrice
Incluye índice
Wehave trained and tested a number of large neural networks for the purpose of emission probability estimation in large vocabulary continuous speech recognition. In particular, the problem under test...
Nikki Mirghafori And, Nikki Mirghafori, Nelson Morgan
Multi-band automatic speech recognition is a new and exploratory area of speech recognition which has been getting much attention in the research community. It has been shown that multiband ASR...
The Berkeley Restaurant Project
Daniel Jurafsky Chuck, Chuck Wooters, Gary Tajchman, Jonathan Segal, Andreas Stolcke, Eric Fosler, ...
This paper describes the architecture and performance of the Berkeley Restaurant Project (BeRP), a medium-vocabulary, speaker-independent, spontaneous continuous speech understanding system currently...
A New Training Algorithm For Hybrid HMM/ANN Speech Recognition Systems
Hervé Bourlard, Yochai Konig, Nelson Morgan, Christophe Ris
In this paper, we briefly describe REMAP, an approach for the training and estimation of posterior probabilities, and report its application to speech recognition. REMAP is a recursive algorithm that...