MTTK: an alignment toolkit for statistical machine translation (2009)
The MTTK alignment toolkit for statistical machine translation can be used for word, phrase, and sentence alignment of parallel documents. It is designed mainly for building statistical machine...
Fang Zheng, Zhanjiang Song, Pascale Fung, William Byrne
The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. By studying the initial/final (IF)...
MANDARIN PRONUNCIATION MODELING BASED ON CASS CORPUS (2008)
Fang Zheng, Zhanjiang Song, Pascale Fung, William Byrne
The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. By studying the initial/final (IF)...
Efficient estimation and alignment procedures for word and phrase alignment HMMs are developed for the alignment of parallel text. The development of these models is motivated by an analysis of the...
The Alignment Template Translation Model (2007)
We present a derivation of the alignment template model for statistical machine translation and an implementation of the model using weighted finite state transducers. The approach we describe allows...
At 4:13 A.M. Eastern Standard Time on (2007)
Douglas W. Oard, David Doermann, Bonnie Dorr, Daqing He, Philip Resnik, Amy Weinberg, ...
A Weighted Finite State Transducer Implementation of the Alignment (2007)
Template Model For, Shankar Kumar, William Byrne
We present a derivation of the alignment template model for statistical machine translation and an implementation of the model using weighted finite state transducers. The approach we describe allows...
Minimum Bayes-Risk Decoding for Statistical Machine Translation (2007)
Kumar, Shankar, Byrne, William
We present Minimum Bayes-Risk (MBR) decoding for statistical machine translation. This statistical approach aims to minimize expected loss of translation errors under loss functions that measure...
Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition (2006)
Minimum Bayes risk estimation and decoding strategies based on lattice segmentation techniques can be used to refine large vocabulary continuous speech recognition systems through the estimation of...
Local phrase reordering models for statistical machine translation (2005)
Shankar Kumar, William Byrne, Speech Processing
We describe stochastic models of local phrase movement that can be incorporated into a Statistical Machine Translation (SMT) system. These models provide properly formulated, non-deficient,...
Lattice Segmentation and Minimum Bayes (2005)
Risk Discriminative Training, Vlasios Doumpiotis, William Byrne
Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech recognition tasks are used to compute the statistics for discriminative training algorithms that...
Lattice segmentation and minimum Bayes risk discriminative training (2005)
Vlasios Doumpiotis, William Byrne
Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech recognition tasks are used to compute the statistics needed for discriminative training algorithms...
Convergence theorems for generalized alternating minimization procedures (2005)
Asela Gunawardana, William Byrne
The EM algorithm is widely used to develop iterative parameter estimation procedures for statistical models. In cases where the algorithms strictly follow the EM formulation, the convergence...
Convergence theorems for generalized alternating minimization procedures (2005)
Asela Gunawardana, William Byrne
The EM algorithm is widely used to develop iterative parameter estimation procedures for statistical models. In cases where these procedures strictly follow the EM formulation, the convergence...
Hmm word and phrase alignment for statistical machine translation (2005)
HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently. We find that...
Hmm word and phrase alignment for statistical machine translation (2005)
HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently. We find that...
Local phrase reordering models for statistical machine translation (2005)
Shankar Kumar, William Byrne, Speech Processing
We describe stochastic models of local phrase movement that can be incorporated into a Statistical Machine Translation (SMT) system. These models provide properly formulated, non-deficient,...
Segmental minimum Bayes-risk decoding for automatic speech recognition (2004)
Vaibhava Goel, Shankar Kumar, William Byrne
Minimum Bayes-Risk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum a-posteriori probability (MAP) decoders through N-best list rescoring and ¢¡ search...
Vlasios Doumpiotis, William Byrne
Iterative estimation procedures that minimize empirical risk based on general loss functions such as the Levenshtein distance have been derived as extensions of the Extended Baum Welch algorithm....
Minimum Bayes-Risk Decoding for Statistical Machine Translation (2004)
Shankar Kumar, William Byrne, Speech Processing
We present Minimum Bayes-Risk (MBR) decoding for statistical machine translation. This statistical approach aims to minimize expected loss of translation errors under loss functions that measure...
Pinched Lattice Minimum Bayes Risk Discriminative Training for Large (2004)
Vocabulary Continuous Speech, Vlasios Doumpiotis, William Byrne
Iterative estimation procedures that minimize empirical risk based on general loss functions such as the Levenshtein distance have been derived as extensions of the Extended Baum Welch algorithm....
Task-Specific Minimum Bayes-Risk Decoding using Learned Edit Distance (2004)
Izhak Shafran And, Izhak Shafran, William Byrne
This paper extends the minimum Bayes-risk framework to incorporate a loss function specific to the task and the ASR system. The errors are modeled as a noisy channel and the parameters are learned...
Task-Specific Minimum Bayes-Risk Decoding using Learned Edit Distance (2004)
This paper extends the minimum Bayes-risk framework to incorporate a loss function specific to the task and the ASR system. The errors are modeled as a noisy channel and the parameters are learned...
Minimum bayes-risk decoding for statistical machine translation (2004)
Shankar Kumar, William Byrne, Speech Processing
We present Minimum Bayes-Risk (MBR) decoding for statistical machine translation. This statistical approach aims to minimize expected loss of translation errors under loss functions that measure...
Discriminative training for segmental minimum Bayes risk decoding (2003)
Vlasios Doumpiotis, Stavros Tsakalidis, William Byrne
A modeling approach is presented that incorporates discriminative training procedures within segmental Minimum Bayes-Risk decoding (SMBR). SMBR is used to segment lattices produced by a general...
GiniSupport Vector Machines for Segmental (2003)
Minimum Bayes Risk, Veera Venkataramani, Shantanu Chakrabartty, William Byrne
We describe the use of Support Vector Machines (SVMs) for continuous speech recognition by incorporating them in Segmental Minimum Bayes Risk decoding. Lattice cutting is used to convert the...
Lattice Segmentation and Minimum Bayes Risk Discriminative Training (2003)
Vlasios Doumpiotis Stavros, Stavros Tsakalidis, William Byrne
Modeling approaches are presented that incorporate discriminative training procedures in segmental Minimum Bayes-Risk decoding (SMBR). SMBR is used to segment lattices produced by a general automatic...
Supporting access to large digital oral history archives (2002)
Samuel Gustman, Dagobert Soergel, Douglas Oard, William Byrne, Michael Picheny, Bhuvana Ramabhadran, ...
This paper, describes our experience with the creation, indexing and providing access to a very large archive of videotaped oral histories—116,000 hours of digitized interviews in 32 languages from...
Supporting access to large digital oral history archives (2002)
Samuel Gustman, Dagobert Soergel, Douglas Oard, William Byrne, Michael Picheny, Bhuvana Ramabhadran, ...
This paper describes our experience with the creation, indexing, and provision of access to a very large archive of videotaped oral histories − 116,000 hours of digitized interviews in 32 languages...
Supporting access to large digital oral history archives (2002)
Samuel Gustman, Dagobert Soergel, Douglas Oard, William Byrne, Michael Picheny, Bhuvana Ramabhadran, ...
This paper describes our experience with the creation, indexing, and provision of access to a very large archive of videotaped oral histories- 116,000 hours of digitized interviews in 32 languages...
Risk based lattice cutting for segmental minimum Bayes-risk decoding (2002)
Minimum Bayes-Risk (MBR) speech recognizers have been shown to give improvements over the conventional maximum a-posteriori probability (MAP) decoders through N-best list rescoring and search over...
Minimum Bayes-risk word alignments of bilingual texts (2002)
Shankar Kumar, William Byrne, Speech Processing
We present Minimum Bayes-Risk word alignment for machine translation. This statistical, model-based approach attempts to minimize the expected risk of alignment errors under loss functions that...
Stavros Tsakalidis, Vlasios Doumpiotis, William Byrne
Linear transforms have been used extensively for training and adaptation of HMM-based ASR systems. Recently procedures have been developed for the estimation of linear transforms under the Maximum...
Wayne Ward, Holly Krech, Xiuyang Yu, Keith Herold, George Figgs, Ayako Ikeno, ...
We report on our preliminary experiments on building dynamic lexicons for native-speaker conversational speech and for foreign-accented conversational speech. Our goal is to build a lexicon with a...
Minimum Bayes-Risk Word Alignments of Bilingual Texts (2002)
Shankar Kumar And, Shankar Kumar, William Byrne, Speech Processing
We present Minimum Bayes-Risk word alignment for machine translation. This statistical, model-based approach attempts to minimize the expected risk of alignment errors under loss functions that...
Confidence based lattice segmentation and minimum Bayes-risk decoding (2001)
Vaibhava Goel, Shankar Kumar, William Byrne
Minimum Bayes Risk (MBR) speech recognizers have been shown to yield improvements over the conventional maximum a-posteriori probability (MAP) decoders in the context of Nbest list rescoring and...
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
Mandarin Pronunciation Modeling Based On Cass Corpus (2001)
Fang Zheng, Zhanjiang Song, Fang Zheng (郑方, Zhanjiang Song (宋战江, Pascale Fung, William Byrne
The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. In this paper, the factors that may affect the...
Pronunciation modeling of mandarin casual speech – final report (2000)
Pascale Fung, William Byrne, Zheng Fang Thomas, Terri Kamm, Liu Yi, Song Zhanjiang, ...
Current ASR systems can usually reach an accuracy of above 90 % when evaluated on carefully read standard speech, but only around 75 % on broadcast news speech. Broadcast news consists of utterances...
Towards Language Independent Acoustic Modeling (1999)
William Byrne, P. Beyerlein, J.M. Huerta, Sanjiv Khudanpur, S. Khudanpur, B. Marthi, ...
We describe procedures and experimental results using speechfrom diverse source languages to build an ASR system for a single target language. This work is intended to improve ASR in languages for...
Discounted Likelihood Linear Regression For Rapid Adaptation (1999)
William Byrne, Asela Gunawardana, N. Charles St
Rapid adaptation schemes that employ the EM algorithm may suffer from overtraining problems when used with small amounts of adaptation data. An algorithm to alleviate this problem is derived within...
Task Dependent Loss Functions In Speech Recognition: Application To Named Entity Extraction (1999)
Vaibhava Goel William, William Byrne
We present a risk-based decoding strategy for the task of Named Entity identification from speech. This approach does not select the most likely utterance produced by an ASR system, which would be...
Task Dependent Loss Functions In Speech Recognition: Application To Named Entity Extraction (1999)
We present a risk-based decoding strategy for the task of Named Entity identification from speech. This approach does not select the most likely utterance produced by an ASR system, which would be...
Speaker normalization with all-pass transforms (1998)
John Mcdonough, William Byrne, Xiaoqiang Luo
Speaker normalization is a process in which the short-time features of speech from a given speaker are transformed so as to better match some speaker independent model. Vocal tract length...
LVCSR Rescoring With Modified Loss Functions: A Decision Theoretic Perspective (1998)
Vaibhava Goel, William Byrne, Sanjeev Khudanpur
The problem of speech decoding is considered here in a Decision Theoretic framework and a modified speech decoding procedure to minimize the expected risk under a general loss function is formulated....
William Byrne, Eva Knodt, Sanjeev Khudanpur, Jared Bernstein
We describe the protocol used for collecting a corpus of conversational English speech from non-native speakers at several levels of proficiency, and report the results of preliminary automatic...
Information Geometry and Maximum Likelihood Criteria (1996)
This paper presents a brief comparison of two information geometries as they are used to describe the EM algorithm used in maximum likelihood estimation from incomplete data. The Alternating...
It is shown here that several techniques for masimum likelihood training of Hidden Markov Models are instances of the EM algorithm and have very similar descriptions when formulated as instances of...
Generalization And Maximum Likelihood From Small Data Sets (1993)
INTRODUCTION An often encountered learning problem is maximum likelihood training of exponential models. When the state is only partially specified by the training data, iterative training algorithms...