Kornel Laskowski, Mari Ostendorf, Tanja Schultz
An important task in automatic conversation understanding is the inference of social structure governing participant behavior. We explore the dependence between several social dimensions, including...
Agreement/Disagreement Classification: Exploiting Unlabeled Data using Contrast Classifiers (2009)
Sangyun Hahn, Richard Ladner, Mari Ostendorf
Several semi-supervised learning methods have been proposed to leverage unlabeled data, but imbalanced class distributions in the data set can hurt the performance of most algorithms. In this paper,...
Özgür Çetin, Mari Ostendorf, Gary D. Bernard
Abstract — This paper introduces multi-rate coupled hidden Markov models (multi-rate HMMs for short) for multiscale modeling of nonstationary processes, extending traditional HMMs from single to...
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]
Yang Liu, Elizabeth Shriberg, Andreas Stolcke, Senior Member, Dustin Hillard, Mari Ostendorf, ...
Abstract — Effective human and automatic processing of speech requires recovery of more than just the words. It also involves recovering phenomena such as sentence boundaries, filler words, and...
MULTI-RATE HIDDEN MARKOV MODELS AND THEIR APPLICATION TO MACHINING TOOL-WEAR CLASSIFICATION (2008)
This paper introduces a multi-rate hidden Markov model (multirate HMM) for multi-scale stochastic modeling of non-stationary processes. The multi-rate HMM decomposes the process variability into...
The ISL RT-06S Speech-to-Text System (2008)
Fügen, Christian, Ikbal, Shajith, Kraft, Florian, Kumatani, Kenichi, Laskowski, Kornel, McDonough, John, ...
Advances in Lecture Recognition: The ISL RT-06S Evaluation System (2008)
Fügen, Christian, Wölfel, Matthias, McDonough, John, Ikbal, Shajith, Kraft, Florian, Laskowski, Kornel, ...
The ISL RT-06S Speech-to-Text System (2008)
Christian Fügen, Shajith Ikbal, Florian Kraft, Kenichi Kumatani, John W. Mcdonough, Mari Ostendorf, ...
Abstract. This paper describes the 2006 lecture and conference meeting speech-to-text system developed at the Interactive Systems Laboratories (ISL), for the individual head-mounted microphone (IHM),...
Liu1;5 STRUCTURAL METADATA RESEARCH IN THE EARS PROGRAM (2008)
Yang Elizabeth, Shriberg Andreas Stolcke, Barbara Peskin, Jeremy Ang, Dustin Hillard, Mari Ostendorf, ...
Both human and automatic processing of speech require recognition of more than just words. In this paper we provide a brief overview of research on structural metadata extraction in the DARPA EARS...
doi: 10.1016/S0885-2308(02)00023-2 (2008)
Efficient integrated response generation from multiple targets using weighted finite state transducers
Flexible Speech Synthesis Using Weighted Finite State Transducers (2008)
Mari Ostendorf, Mari Ostendorf, Alex Acero, Jeffrey Bilmes, Ivan Bulyko
and that any and all revisions required by the final examining committee have been made.
ACCOUNTING FOR STT UNCERTAINTY IN MDE (2008)
Dustin Hillard, Mari Ostendorf
We extend existing methods for automatic sentence boundary detection by leveraging multiple recognizer hypotheses in order to provide robustness to speech recognition errors. For each hypothesized...
Mari Ostendorf, Barbara Peskin, Mary Harper
Both human and automatic processing of speech require recognizing more than just the words. We describe a state-of-the-art system for automatic detection of “metadata ” (information beyond the...
HUMAN LANGUAGE TECHNOLOGY: OPPORTUNITIES AND CHALLENGES (2008)
Mari Ostendorf, Elizabeth Shriberg, Andreas Stolcke
In recent years, there has been dramatic progress in both speech and language processing, in many cases leveraging some of the same underlying methods. This progress and the growing technical ties...
Speaker Clustered Regression-Class Trees for MLLR Adaptation (2008)
Arindam M, Mari Ostendorf, Andreas Stolcke
A speaker clustering algorithm is presented that is based on an eigenspace representation of Maximum Likelihood Linear Regression (MLLR) transformations and is used for training cluster-dependent...
Liu1;5 STRUCTURAL METADATA RESEARCH IN THE EARS PROGRAM (2008)
Yang Elizabeth, Shriberg Andreas Stolcke, Barbara Peskin, Jeremy Ang, Dustin Hillard, Mari Ostendorf, ...
Both human and automatic processing of speech require recognition of more than just words. In this paper we provide a brief overview of research on structural metadata extraction in the DARPA EARS...
Current speech recognition systems perform poorly on conversational speech as compared to read speech, arguably due to the large acoustic variability inherent in conversational speech. Our hypothesis...
Liu1;5 STRUCTURAL METADATA RESEARCH IN THE EARS PROGRAM (2008)
Yang Elizabeth, Shriberg Andreas Stolcke, Barbara Peskin, Jeremy Ang, Dustin Hillard, Mari Ostendorf, ...
Both human and automatic processing of speech require recognition of more than just words. In this paper we provide a brief overview of research on structural metadata extraction in the DARPA EARS...
Mari Ostendorf, Barbara Peskin, Mary Harper
Both human and automatic processing of speech require recognizing more than just the words. We describe a state-of-the-art system for automatic detection of “metadata ” (information beyond the...
Punctuating speech for information extraction (2008)
Benoit Favre, Ralph Grishman, Dustin Hillard, Heng Ji, Dilek Hakkani-tür, Mari Ostendorf
This paper studies the effect of automatic sentence boundary detection and comma prediction on entity and relation extraction in speech. We show that punctuating the machine generated transcript...
Boeing Commercial Airplane Group (2007)
Les Atlas, Mari Ostendorf, Gary D. Bernard
As summarized by Atlas, Bernard, and Narayanan [1], the sensing of acoustic vibrations can remotely estimate the state of wear at the tool edge. This form of monitoring offers the potential to...
Ivan Bulyko, Mari Ostendorf, Mari Ostendorf, Alex Acero
This is to certify that I have examined this copy of a doctoral dissertation by
Current speech recognition systems perform poorly on conversational speech as compared to read speech, arguably due to the large acoustic variability inherent in conversational speech. Our hypothesis...
Article Submitted to Computer Speech and Language Normalization of Non-Standard Words (2007)
Richard Sproat, Alan W Black, Stanley Chen, Shankar Kumar, Mari Ostendorf
In addition to ordinary words and names, real text contains non-standard:'words " (NSW's), including numbers, abbreviations, dates, currency amounts and acronyms. Typically, one...
Ivan Bulyko, Mari Ostendorf, Julie Goldberg, Katrin Kirchhoff
Abstract goes here. 1.
Article Submitted to Computer Speech and Language (2007)
Acoustic Model Clustering, Izhak Shafran, Mari Ostendorf
Current speech recognition systems perform poorly on conversational speech as compared to read speech, arguably due to the large acoustic variability inherent in conversational speech. Our hypothesis...
Parsing Conversational Speech Using Enhanced Segmentation (2007)
Kahn, Jeremy G., Ostendorf, Mari, Chelba, Ciprian
The lack of sentence boundaries and presence of disfluencies pose difficulties for parsing conversational speech. This work investigates the effects of automatically detecting these phenomena on a...
Detecting Structural Metadata with Decision Trees and Transformation-Based Learning (2007)
Kim, Joungbum, Schwarm, Sarah E., Ostendorf, Mari
The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness of spontaneous...
Language Modeling With Sentence-Level Mixtures (2007)
Iyer, Rukmini, Ostendorf, Mari, Rohlicek, J. R.
This paper introduces a simple mixture language model that attempts to capture long distance constraints in a sentence or paragraph. The model is an m-component mixture of trigram models. The models...
The Use of Prosody in Syntactic Disambiguation (2007)
Price, Patti, Ostendorf, Mari, Shattuck-Hufnagel, Stefanie, Fong, Cynthia
Prosodic structure and syntactic structure are not identical; neither are they unrelated. Knowing when and how the two correspond could yield better quality speech synthesis, could aid in the...
Weight Estimation for N-Best Rescoring (2007)
Kannan, Ashvin, Ostendorf, Mari, Rohlicek, J. R.
This paper describes recent improvements in the weight estimation technique for sentence hypothesis rescoring using the N-Best formalism. Mismatches between training and test data are also explored.
Building a highly accurate Mandarin speech recognizer (2007)
Mei-yuh Hwang, Gang Peng, Wen Wang, Arlo Faria, Aaron Heidel, Mari Ostendorf
We describe a highly accurate large-vocabulary continuous Mandarin speech recognizer, a collaborative effort among four research organizations. Particularly, we build two acoustic models (AMs) with...
Arindam Mandal, Arindam Mandal, Mari Ostendorf, Mari Ostendorf, Andreas Stolcke, Jeffrey Bilmes, ...
This is to certify that I have examined this copy of a doctoral dissertation by
Reading Level Assessment and Text Simplification (2007)
Sarah E. Petersen, Sarah E. Petersen, Mari Ostendorf, Mari Ostendorf, Oren Etzioni, Henry Kautz, ...
This is to certify that I have examined this copy of a doctoral dissertation by
Improving speech translation with automatic boundary prediction (2007)
Evgeny Matusov, Dustin Hillard, Mathew Magimai-doss, Dilek Hakkani-tur, Mari Ostendorf, Hermann Ney
This paper investigates the influence of automatic sentence boundary and sub-sentence punctuation prediction on machine translation (MT) of automatically recognized speech. We use prosodic and...
Text simplification for language learners: a corpus analysis (2007)
Sarah E. Petersen, Mari Ostendorf
Simplified texts are commonly used by teachers and students in bilingual education and other language-learning contexts. These texts are usually manually adapted, and teachers say this is a...
Segment-Based Acoustic Models for Continuous Speech Recognition (2006)
Ostendorf, Mari, Rohlicek, J. R.
This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition by extending previous work in segment-based modeling and by introducing a...
Segment-Based Acoustic Models for Continuous Speech Recognition (2006)
Ostendorf, Mari, Rohlicek, J. R.
This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition by extending previous work in segment-based modeling and by introducing a...
Segment-Based Acoustic Models for Continuous Speech Recognition (2006)
Ostendorf, Mari, Rohlicek, J. R.
In work, we are interested in the problem of large vocabulary, speaker-independent continuous speech recognition, and primarily in the acoustic modeling component of this problem. In developing...
Recognition Using Classification and Segmentation Scoring (2006)
Kimball, Owen, Ostendorf, Mari, Rohlicek, Robin
Traditional statistical speech recognition systems typically make strong assumptions about the independence of observation frames and generally do not make use of segmental information. In contrast,...
Advances in Lecture Recognition: The ISL RT-06S Evaluation System. (2006)
Fügen, Christian, Wölfel, Matthias, McDonough, John, Ikbal, Shajith, Kraft, Florian, Laskowski, Kornel, ...
The ISL RT-06S Speech-to-Text System. (2006)
Fügen, Christian, Ikbal, Shajith, Kraft, Florian, Kumatani, Kenichi, Laskowski, Kornel, McDonough, John, ...
A machine learning approach to reading level assessment (2006)
Sarah E. Petersen, Mari Ostendorf
Reading proficiency is a fundamental component of language competency. However, finding topical texts at an appropriate reading level for foreign and second language learners is a challenge for...
Parse structure and segmentation for improving speech recognition (2006)
William P. Mcneill, Jeremy G. Kahn, Dustin L. Hillard, Mari Ostendorf
Separate avenues of prior work have shown that parsing language models lead to improved recognition performance, and that segmentation of speech into sentence-like units has an impact on parser...
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
Processing Hlt Emnlp, Eugene Charniak, Mark Johnson, Mari Ostendorf
We identify a set of prosodic cues for parsing conversational speech and show how such features can be effectively incorporated into a statistical parsing model. On the Switchboard corpus of...
DBN multistream models for Mandarin toneme recognition (2005)
Xin Lei, Gang Ji, Tim Ng, Jeff Bilmes, Mari Ostendorf
A toneme in Mandarin Chinese is a tonal phone which consists of a base phone (main vowel) and a tone. To capture both, most recognition systems use two feature streams: the standard MFCCs for the...
Structural Metadata Research in the EARS Program (2005)
Yang Liu, Elizabeth Shriberg, Andreas Stolcke, Barbara Peskin, Jeremy Ang, Dustin Hillard, ...
Both human and automatic processing of speech require recognition of more than just words. In this paper we provide a brief overview of research on structural metadata extraction in the DARPA EARS...
Leveraging speakerdependent variation of adaptation (2005)
This work introduces an automatic procedure for determining the size of regression class trees for individual speakers using an ensemble of speaker-level features to control the number of...
A quantitative analysis of lexical differences between genders in telephone conversations (2005)
Constantinos Boulis, Mari Ostendorf
In this work, we provide an empirical analysis of differences in word use between genders in telephone conversations, which complements the considerable body of work in sociolinguistics concerned...
Reading Level Assessment Using Support Vector Machines and Statistical Language Models (2005)
Sarah E. Schwarm, Mari Ostendorf
Reading proficiency is a fundamental component of language competency. However, finding topical texts at an appropriate reading level for foreign and second language learners is a challenge for...
Combining multiple clustering systems (2004)
Constantinos Boulis, Mari Ostendorf
Abstract. Three methods for combining multiple clustering systems are presented and evaluated, focusing on the problem of finding the correspondence between clusters of different systems. In this...
Detecting structural metadata with decision trees and transformation-based learning (2004)
Joungbum Kim, Sarah E. Schwarm, Mari Ostendorf
The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness of spontaneous...
Özgür Çetin, Özgür Çetin, Mari Ostendorf, Mari Ostendorf, Jeffrey A. Bilmes, Maya R. Gupta, ...
and have found that it is complete and satisfactory in all respects, Chair of Supervisory Committee: Reading Committee:
Progress on mandarin conversational telephone speech recognition (2004)
Mei-yuh Hwang, Xin Lei, Tim Ng, Ivan Bulyko, Mari Ostendorf, Andreas Stolcke, ...
Over the past decade, there has been good progress on English conversational telephone speech (CTS) recognition, built on the Switchboard and Fisher corpora. In this paper, we present our efforts on...
From switchboard to meetings: Development of the 2004 icsi-sri-uw meeting recognition system (2004)
Nikki Mirghafori, Andreas Stolcke, Chuck Wooters, Tuomo Pirinen, Dave Gelbart, Martin Graciarena, ...
Progress in Meeting Recognition: The ICSI-SRI-UW Spring 2004 Evaluation System (2004)
Andreas Stolcke, Chuck Wooters, Nikki Mirghafori, Tuomo Pirinen, Ivan Bulyko, Dave Gelbart, ...
We describe the ICSI-SRI-UW team's entry in the Spring 2004 NIST Meeting Recognition Evaluation. The system was derived from SRI's 5xRT Conversational Telephone Speech (CTS) recognizer by...
Disfluencies, and Conversational Fillers in Spontaneous Speech (2004)
Mari Ostendorf, Katrin Kirchhoff, Joungbum Kim, Joungbum Kim, Joungbum Kim
Automatic Detection of Sentence Boundaries, Disfluencies, and Conversational Fillers in Spontaneous Speech Joungbum Kim Chair of Supervisory Committee: Professor Mari Ostendorf Electrical Engineering...
The ICSI-SRI-UW metadata extraction system (2004)
Yang Liu, Elizabeth Shriberg, Andreas Stolcke, Dustin Hillard, Mari Ostendorf, Barbara Peskin, ...
Both human and automatic processing of speech require recognizing more than just the words. We describe a state-of-the-art system for automatic detection of “metadata ” (information beyond the...
M.: Progress in meeting recognition: The ICSI-SRI-UW Spring 2004 evaluation system (2004)
Andreas Stolcke, Chuck Wooters, Nikki Mirghafori, Tuomo Pirinen, Dave Gelbart, Martin Graciarena, ...
We describe the ICSI-SRI-UW team’s entry in the Spring 2004 NIST Meeting Recognition Evaluation. The system was derived from SRI’s 5xRT Conversational Telephone Speech (CTS) recognizer by...
From switchboard to meetings: Development of the 2004 icsi-sri-uw meeting recognition system (2004)
Nikki Mirghafori, Andreas Stolcke, Chuck Wooters, Tuomo Pirinen, Ivan Bulyko, Dave Gelbart, ...
M.: Progress in meeting recognition: The ICSI-SRI-UW Spring 2004 evaluation system (2004)
Andreas Stolcke, Chuck Wooters, Nikki Mirghafori, Tuomo Pirinen, Ivan Bulyko, Dave Gelbart, ...
We describe the ICSI-SRI-UW team’s entry in the Spring 2004 NIST Meeting Recognition Evaluation. The system was derived from SRI’s 5xRT Conversational Telephone Speech (CTS) recognizer by...
Improving automatic sentence boundary detection with confusion networks (2004)
We extend existing methods for automatic sentence boundary detection by leveraging multiple recognizer hypotheses in order to provide robustness to speech recognition errors. For each hypothesized...
Detection of agreement vs. disagreement in meetings: Training with unlabeled data (2003)
Dustin Hillard, Mari Ostendorf
To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that...
Detection of agreement vs. disagreement in meetings: Training with unlabeled data (2003)
Dustin Hillard, Mari Ostendorf
To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that...
Word selection for ebmt based on monolingual similarity and translation (2003)
Shazia Akhtar, Ronan G. Reilly, Mari Ostendorf, Yaser Al-onaizan, Radu Florian, ...
[4] Hiyan Alshawi. Effective utterance classification with unsupervised phonotactic
Classdependent interpolation for estimating language models from multiple text sources (2003)
Ivan Bulyko, Ivan Bulyko, Mari Ostendorf, Mari Ostendorf, Andreas Stolcke, Andreas Stolcke
Sources of training data suitable for language modeling of conversational speech are limited. In this paper, we show how training data can be supplemented with text from the web filtered to match the...
The impact of response wording in error correction subdialogs (2003)
Julie Goldberg, Mari Ostendorf, Katrin Kirchhoff
Spoken human-machine dialogs are prone to communication failures due to imperfect speech recognition and understanding. In order to recover from these failures, users typically engage in error...
Sources of training data suitable for language modeling of conversational speech are limited. In this paper, we show how training data can be supplemented with text from the web filtered to match the...
Detection of agreement vs. disagreement in meetings: Training with unlabeled data (2003)
Dustin Hillard, Mari Ostendorf
To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that...
Chair of Supervisory Committee: (2003)
Mari Ostendorf, Mari Ostendorf, Katrin Kirchho, Michael Riley, Richard Wright, Rebecca Anne Bates, ...
Speaker dynamics as a source of pronunciation variability for continuous speech recognition models
Directions for Multi-Party Human-Computer Interaction Research (2003)
Katrin Kirchhoff, Mari Ostendorf
Research on dialog systems has so far concentrated on interactions between a single user and a machine. In this paper we identify novel research directions arising from multi-party human computer...
Prosody models for conversational speech recognition (2003)
Mari Ostendorf, Izhak Shafran, Rebecca Bates
This paper describes a formal model for incorporating prosody in the speech recognition process, both for improving word recognition directly and for jointly recognizing words and underlying...
Towards Robust and Adaptive Speech Recognition Models (2002)
Bourlard, H., Bengio, S., Weber, K., Ostendorf, Mari, Khudanpur, Sanjeev, Rosenfeld, Roni
Graceful degradation of speech recognition performance over packet-erasure networks (2002)
Constantinos Boulis, Mari Ostendorf, Eve A. Riskin, Senior Member, Senior Member, Scott Otterson
Abstract—This paper explores packet loss recovery for automatic speech recognition (ASR) in spoken dialog systems, assuming an architecture in which a lightweight client communicates with a remote...
Graceful degradation of speech recognition performance over packet-erasure networks (2002)
Constantinos Boulis, Mari Ostendorf, Eve A. Riskin, Scott Otterson
This paper explores packet loss recovery for automatic speech recognition (ASR) in spoken dialog systems, assuming an architecture in which a lightweight client communicates with a remote ASR server....
Prosody Models for Conversational Speech Recognition (2002)
Mari Ostendorf, Izhak Shafran, Rebecca Bates
This paper describes a formal model for incorporating prosody in the speech recognition process, both for improving word recognition directly and for jointly recognizing words and underlying...
Robust Splicing Costs And Efficient Search With (2002)
Bmm Models For, Ivan Bulyko, Mari Ostendorf, Jeff Bilmes
With the growing popularity of corpus-based methods for concatenative speech synthesis, a large amount of interest has been placed on borrowing techniques from the ASR community. This paper explores...
The 2001 GMTK-Based Spine ASR System (2002)
Özgür Cetin, Harriet J. Nock, Katrin Kirchhoff, Jeff Bilmes, Mari Ostendorf
This paper provides a detailed description of the University of Washington automatic speech recognition (ASR) system for the 2001 DARPA SPeech In Noisy Environments (SPINE) task. Our system makes...
The 2001 GMTK-based SPINE ASR system (2002)
Özgür Çetin, Harriet J. Nock, Katrin Kirchhoff, Jeff Bilmes, Mari Ostendorf
This paper provides a detailed description of the University of Washington automatic speech recognition (ASR) system for the 2001 DARPA SPeech In Noisy Environments (SPINE) task. Our system makes...
Text normalization with varied data sources for conversational speech language modeling (2002)
Collecting sufficient language model training data for good speech recognition performance in a new domain is often difficult. However, there may be other sources of data that are matched in terms of...
Prosody and phonetic variability: Lessons learned from acoustic model clustering (2001)
Izhak Shafran, Mari Ostendorf, Richard Wright
Most research on the use of prosody in automatic speech processing has focused on F0, energy and duration correlates to prosodic structure. However, there are multiple sources of evidence suggesting...
Graceful Degradation of Speech Recognition Performance Over Lossy Packet Networks (2001)
Eve A. Riskin, Constantinos Boulis, Scott Otterson, Mari Ostendorf
This paper explores packet loss recovery in client-server Automatic Speech Recognition (ASR) systems. A forward error correction (FEC) system is designed and tested over several channel loss models,...
Graceful Degradation of Speech Recognition Performance Over Lossy Packet Networks (2001)
Eve A. Riskin, Constantinos Boulis, Scott Otterson, Mari Ostendorf
This paper explores packet loss recovery in client-server Automatic Speech Recognition (ASR) systems. A forward error correction (FEC) system is designed and tested over several channel loss models,...
Clustering Wide-Contexts and HMM Topologies (2001)
Mari Ostendorf, Je Bilmes, William Byrne, Izhak Shafran, Izhak Shafran, Izhak Shafran
This is to certify that I have examined this copy of a doctoral dissertation by
Use of higher level linguistic structure in acoustic modeling for speech recognition (2000)
Current speech recognition systems perform poorly on conversational speech as compared to read speech, largely because of the additional acoustic variability observed in conversational speech. Our...
Use of higher level linguistic structure in acoustic modeling for speech recognition (2000)
Current speech recognition systems perform poorly on conversational speech as compared to read speech, largely because of the additional acoustic variability observed in conversational speech. Our...
Experiencees of single people working internationally : focus on crisis and trauma / (1999)
Includes bibliographical references (leaves 50-52).
Dr. Mari Ostendorf, Associate Professor
First and foremost, I would like to thank my advisor, Mari Ostendorf. Even after spending several years working in the lab with her, her commitment to quality of writing and research as well as her...
Information Extraction from Broadcast News Speech Data (1999)
David D. Palmer, John D. Burger, Mari Ostendorf
1 The MITRE Corporation In this paper we describe a robust algorithm for information extraction from spoken language data. Our probabilistic algorithm builds on results in language modeling, using...
Predicting gradient F0 variation: pitch range and accent prominence (1999)
Many aspects of prosody prediction in speech synthesis could be improved, from placement of symbolic accent and phrase boundary markers to control of continuously varying parameters (e.g., duration,...
Normalization of Non-Standard Words: WS '99 Final Report (1999)
Richard Sproat, Alan Black, Stanley Chen, Shankar Kumar, Mari Ostendorf, Christopher Richards
All areas of language and speech technology must deal, in one way or another, with real text. Real text is messy: many things one nds in text | numbers, abbreviations, dates, currency amounts,...
Robust Information Extraction From Spoken Language Data (1999)
David D. Palmer, Mari Ostendorf, John D. Burger
In this paper we address the problem of information extraction from speech data, particularly improving robustness to automatic recognition errors. We describe a baseline probabilistic model that...
Predicting gradient F0 variation: pitch range and accent prominence (1999)
Many aspects of prosody prediction in speech synthesis could be improved, from placement ofsymbolic accent and phrase boundary markers to control of continuously varying parameters (e.g., duration,...
SABLE: A Standard For TTS Markup (1998)
Sproat, Richard, Hunt, Andrew, Ostendorf, Mari, Taylor, Paul, Black, Alan W, Lenzo, Kevin, ...
Currently, speech synthesizers are controlled by a multitude of proprietary tag sets. These tag sets vary substantially across synthesizers and are an inhibitor to the adoption of speech synthesis...
SABLE: A Standard For TTS Markup (1998)
Sproat, Richard, Hunt, Andrew, Ostendorf, Mari, Taylor, Paul, Black, Alan W, Lenzo, Kevin, ...
Currently, speech synthesizers are controlled by a multitude of proprietary tag sets. These tag sets vary substantially across synthesizers and are an inhibitor to the adoption of speech synthesis...
SABLE: A Standard for TTS Markup (1998)
Sproat, Richard, Hunt, Andrew, Ostendorf, Mari, Taylor, Paul, Black, Alan W, Lenzo, Kevin, ...
Currently, speech synthesizers are controlled by a multitude of proprietary tag sets. These tag sets vary substantially across synthesizers and are an inhibitor to the adoption of speech synthesis...
SABLE: A Standard for TTS Markup (1998)
Sproat, Richard, Hunt, Andrew, Ostendorf, Mari, Taylor, Paul, Black, Alan W, Lenzo, Kevin, ...
Currently, speech synthesizers are controlled by a multitude of proprietary tag sets. These tag sets vary substantially across synthesizers and are an inhibitor to the adoption of speech synthesis...
Segment-Based Acoustic Models for Continuous Speech Recognition. (1998)
Ostendorf, Mari, Rohlicek, J. R.
This paper presents an overview of the Boston University continuous word recognition system, which is based on the Stochastic Segment Model (SSM). The key components of the system described here...
Segment-Based Acoustic Models for Continuous Speech Recognition. (1998)
Ostendorf, Mari, Rohlicek, J. R.
This research aims to develop new and more accurate acoustic models for speaker-independent continuous speech recognition, by extending previous work in segment-based modeling and by introducing a...
Segment-Based Acoustic Models for Continuous Speech Recognition. (1998)
Ostendorf, Mari, Rohlicek, J. R.
This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition, by extending previous work in segment-based modeling and by introducing a...
Segment-Based Acoustic Models for Continuous Speech Recognition. (1998)
Ostendorf, Mari, Rohlicek, J. R.
This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition by extending previous work in segment-based modeling, by introducing a new...
Segment-Based Acoustic Models for Continuous Speech Recognition. (1998)
Ostendorf, Mari, Rohlicek, J. R.
This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition by extending previous work in segment-based modeling, by introducing a new...
Human Language Technology: Opportunities and Challenges (1998)
Ostendorf, Mari, Shriberg, Elizabeth, Stolcke, Andreas
In recent years, there has been dramatic progress in both speech and language processing, in many cases leveraging some of the same underlying methods. This progress and the growing technical ties...
Structural Metadata Research in the Ears Program (1998)
Liu, Yang, Shriberg, Elizabeth, Stolcke, Andreas, Peskin, Barbara, Ang, Jeremy, Hillard, Dustin, ...
Both human and automatic processing of speech require recognition of more than just words. In this paper we provide a brief overview of research on structural metadata extraction in the DARPA EARS...
Improving And Predicting Performance Of Statistical Language Models In Sparse Domains (1998)
Rukmini M. Iyer, Rukmini M. Iyer, Dr. Mari Ostendorf, Associate Professor
Standard statistical language models, or n-gram models, which represent the probability of word sequences, suffer from sparse-data problems in tasks where large amounts of domain-specific text are...
Automatic Detection Of Sentence Boundaries And Disfluencies Based On Recognized Words (1998)
Andreas Stolcke, Elizabeth Shriberg, Rebecca Bates, Mari Ostendorf, Dilek Hakkani, Madelaine Plauche, ...
We study the problem of detecting linguistic events at interword boundaries, such as sentence boundaries and disfluency locations, in speech transcribed by an automatic recognizer. Recovering such...
High-Order Modeling Techniques for Continuous Speech Recognition. (1997)
This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition by developing acoustic and language models aimed at representing high-order...
High-Order Modeling Techniques for Continuous Speech Recognition. (1997)
This research aims to develop new and more accurate stochastic models for speaker independent continuous speech recognition by developing acoustic and language models aimed at representing high-order...
Rebecca Anne Bates, Dr. Mari Ostendorf, Associate Professor, Dr. J. Robin Rohlicek, Vice President, ...
It takes a village to raise a child, it took a village to get this thesis done and written. Apologies for the length of the acknowledgments. Primary acknowledgments must go to Mari Ostendorf, my...
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
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....
Lattice-Based Search Strategies For Large Vocabulary Speech Recognition (1995)
Frederick Richardson, Frederick Richardson, Dr. Mari Ostendorf, Associate Professor, Rich Schwartz, Senior Scientist, ...
The design of search algorithms is an important issue in recognition, particularly for very large vocabulary, continuous speech. It is an especially crucial problem when computationally expensive...
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...
Owen Ashley Kimball, Owenashley Kimball, Dr. Mari Ostendorf, Dr. David Castanon, Associate Professor, Associate Professor
I am indebted to a number of people who helped me in various ways during this work. I would first like to thank my adviser, Mari Ostendorf, for her guidance and support throughout my time at Boston...
A Comparison Of Trajectory And Mixture Modeling In Segment-Based Word Recognition (1993)
This paper presents a mechanism for implementing mixtures at a phone-subsegment (microsegment) level for continuous word recognition based on the Stochastic Segment Model (SSM). We investigate 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.
Continuous Word Recognition Based on the Stochastic Segment Model (1992)
Mari Ostendorf, Ashvin Kannan, Owen Kimball, J. Robin Rohlicek
This paper presents an overview of the Boston University continuous word recognition system, which is based on the Stochastic Segment Model (SSM). The key components of the system described here...
Robust Estimation of Stocchastic Segment Models for Word Recognition (1990)
Ashvin Kannan, Mari Ostendorf, Bolt Beranek, Newman Inc
In this work, we develop robust estimation techniques for a continuous-word recognition system using the Stochastic Segment model (SSM). This work is done under the N-best rescoring formalism, where...
Robust Information Extraction From Spoken Language Data
David D. Palmer, Mari Ostendorf, John D. Burger
In this paper we address the problem of information extraction from speech data, particularly improving robustness to automatic recognition errors. We describe a baseline probabilistic model that...