Ivan Bulyko

发表

Joint prosody prediction and unit selection for concatenative speech synthesis

Mari Ostendorf, Ivan Bulyko, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Class-dependent Interpolation for Estimating Language Models from Multiple Text Sources

Andreas Stolcke, Mari Ostendorf, Ivan Bulyko, 2003 .

Getting More Mileage from Web Text Sources for Conversational Speech Language Modeling using Class-Dependent Mixtures

Andreas Stolcke, Mari Ostendorf, Ivan Bulyko, 2003, NAACL.

Score normalization and system combination for improved keyword spotting

Richard M. Schwartz, John Makhoul, Le Zhang, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion pdf

Ariya Rastrow, Scott Novotney, Linda Liu, 2020, ArXiv.

Web-data augmented language models for Mandarin conversational speech recognition

Mei-Yuh Hwang, Mari Ostendorf, Man-Hung Siu, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Flexible speech synthesis using weighted finite-state transducers

Mari Ostendorf, Ivan Bulyko, Mari Ostendorf, 2002 .

Progress on Mandarin conversational telephone speech recognition

Andreas Stolcke, Wen Wang, Mei-Yuh Hwang, 2004, 2004 International Symposium on Chinese Spoken Language Processing.

Pashto speech recognition with limited pronunciation lexicon

Stavros Tsakalidis, Rohit Prasad, Premkumar Natarajan, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Detection of unseen words in conversational Mandarin

Owen Kimball, Man-Hung Siu, Ivan Bulyko, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Normalizationofphonetic keyword search scores

Richard M. Schwartz, John Makhoul, Stavros Tsakalidis, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Efficient integrated response generation from multiple targets using weighted finite state transducers

Mari Ostendorf, Ivan Bulyko, 2002, Comput. Speech Lang..

PROGRESS IN MEETING RECOGNITION: THE ICSI-SRI-UW SPRING 2004 EVALUATION SYSTEM

Andreas Stolcke, Mari Ostendorf, Martin Graciarena, 2008 .

Subword speech recognition for detection of unseen words

Owen Kimball, Ivan Bulyko, Jose Herrero, 2012, INTERSPEECH.

The impact of speech recognition on speech synthesis

Mari Ostendorf, Ivan Bulyko, Mari Ostendorf, 2002, Proceedings of 2002 IEEE Workshop on Speech Synthesis, 2002..

The effects of speech recognition and punctuation on information extraction performance

Richard M. Schwartz, John Makhoul, Bing Xiang, 2005, INTERSPEECH.

Error-correction detection and response generation in a spoken dialogue system

Mari Ostendorf, Katrin Kirchhoff, Ivan Bulyko, 2005, Speech Commun..

Domain-Aware Neural Language Models for Speech Recognition pdf

Ariya Rastrow, Linda Liu, Ivan Bulyko, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech recognizer optimization under speed constraints

Ivan Bulyko, 2010, INTERSPEECH.

Predicting gradient F0 variation: pitch range and accent prominence

Mari Ostendorf, Ivan Bulyko, 1999, EUROSPEECH.

Improved named entity extraction from conversational speech with language model adaptation

Owen Kimball, Man-Hung Siu, Ivan Bulyko, 2010, 2010 IEEE Spoken Language Technology Workshop.

Multi-task Language Modeling for Improving Speech Recognition of Rare Words pdf

Chao-Han Huck Yang, Linda Liu, Ivan Bulyko, 2020, ArXiv.

Language Model Adaptation in Machine Translation from Speech

Richard M. Schwartz, John Makhoul, Spyridon Matsoukas, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Unit selection for speech synthesis using splicing costs with weighted finite state transducers

Mari Ostendorf, Ivan Bulyko, 2001, INTERSPEECH.

Robust splicing costs and efficient search with BMM Models for concatenative speech synthesis

Jeff A. Bilmes, Mari Ostendorf, Ivan Bulyko, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Semi-Supervised Methods for Improving Keyword Search of Unseen Terms

Richard M. Schwartz, Sanjeev Khudanpur, Owen Kimball, 2012, INTERSPEECH.

Adaptive language modeling with varied sources to cover new vocabulary items

Mari Ostendorf, Ivan Bulyko, Sarah E. Schwarm, 2004, IEEE Transactions on Speech and Audio Processing.

Web resources for language modeling in conversational speech recognition

Andreas Stolcke, Mari Ostendorf, Man-Hung Siu, 2007, TSLP.

From switchboard to meetings: development of the 2004 ICSI-SRI-UW meeting recognition system

Andreas Stolcke, Mari Ostendorf, Martin Graciarena, 2004, INTERSPEECH.

Integrating Speech Recognition and Machine Translation

Richard M. Schwartz, John Makhoul, Spyridon Matsoukas, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

A Likelihood Ratio Based Domain Adaptation Method for E2E Models

Ivan Bulyko, Ankur Gandhe, Chhavi Choudhury, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Towards Continual Entity Learning in Language Models for Conversational Agents pdf

Ivan Bulyko, Ravi Teja Gadde, I. Bulyko, 2021, ArXiv.

Attention-based Contextual Language Model Adaptation for Speech Recognition

Andreas Stolcke, Ariya Rastrow, Scott Novotney, 2021, FINDINGS.

Adjunct-Emeritus Distillation for Semi-Supervised Language Model Adaptation

Scott Novotney, Ivan Bulyko, Yile Gu, 2021, Interspeech.

Domain-Aware Neural Language Models for Speech Recognition

Ariya Rastrow, Linda Liu, Ivan Bulyko, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Personalization Strategies for End-to-End Speech Recognition Systems

Andreas Stolcke, Ariya Rastrow, Linda Liu, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).