Abhinav Sethy
Abhinav Sethy
Amazon Alexa
Verified email at amazon.com
Title
Cited by
Cited by
Year
An approach to real-time magnetic resonance imaging for speech production
S Narayanan, K Nayak, S Lee, A Sethy, D Byrd
The Journal of the Acoustical Society of America 115 (4), 1771-1776, 2004
3572004
Query-by-example spoken term detection for OOV terms
C Parada, A Sethy, B Ramabhadran
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 404-409, 2009
1052009
Topic specific language models built from large numbers of documents
A Sethy, P Georgiou, S Narayanan
US Patent 7,739,286, 2010
1032010
Building topic specific language models from webdata using competitive models
A Sethy, PG Georgiou, S Narayanan
Ninth European Conference on Speech Communication and Technology, 2005
1022005
Refined speech segmentation for concatenative speech synthesis
A Sethy, SS Narayanan
Seventh International Conference on Spoken Language Processing, 2002
832002
System combination and score normalization for spoken term detection
J Mamou, J Cui, X Cui, MJF Gales, B Kingsbury, K Knill, L Mangu, ...
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
812013
End-to-end ASR-free keyword search from speech
K Audhkhasi, A Rosenberg, A Sethy, B Ramabhadran, B Kingsbury
IEEE Journal of Selected Topics in Signal Processing 11 (8), 1351-1359, 2017
772017
Multilingual representations for low resource speech recognition and keyword search
J Cui, B Kingsbury, B Ramabhadran, A Sethy, K Audhkhasi, X Cui, ...
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
742015
Conversion of non-back-off language models for efficient speech decoding
E Arisoy, B Ramabhadran, A Sethy, S Chen
US Patent 9,484,023, 2016
732016
Sparse representation features for speech recognition
TN Sainath, B Ramabhadran, D Nahamoo, D Kanevsky, A Sethy
Eleventh Annual Conference of the International Speech Communication Association, 2010
732010
A new method for OOV detection using hybrid word/fragment system
A Rastrow, A Sethy, B Ramabhadran
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
692009
Effect of pronounciations on OOV queries in spoken term detection
D Can, E Cooper, A Sethy, C White, B Ramabhadran, M Saraclar
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
672009
The IBM 2007 speech transcription system for European parliamentary speeches
B Ramabhadran, O Siohan, A Sethy
2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU …, 2007
642007
Converting neural network language models into back-off language models for efficient decoding in automatic speech recognition
E Arısoy, SF Chen, B Ramabhadran, A Sethy
IEEE/ACM Transactions on Audio, Speech, and Language Processing 22 (1), 184-192, 2013
582013
Knowledge distillation across ensembles of multilingual models for low-resource languages
J Cui, B Kingsbury, B Ramabhadran, G Saon, T Sercu, K Audhkhasi, ...
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
552017
A high-performance Cantonese keyword search system
B Kingsbury, J Cui, X Cui, MJF Gales, K Knill, J Mamou, L Mangu, ...
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
552013
A spoken term detection framework for recovering out-of-vocabulary words using the web
C Parada, A Sethy, M Dredze, F Jelinek
Eleventh Annual Conference of the International Speech Communication Association, 2010
522010
Bidirectional recurrent neural network language models for automatic speech recognition
E Arisoy, A Sethy, B Ramabhadran, S Chen
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
502015
Scaling shrinkage-based language models
SF Chen, L Mangu, B Ramabhadran, R Sarikaya, A Sethy
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 299-304, 2009
472009
Towards using hybrid word and fragment units for vocabulary independent LVCSR systems
A Rastrow, A Sethy, B Ramabhadran, F Jelinek
Tenth Annual Conference of the International Speech Communication Association, 2009
472009
The system can't perform the operation now. Try again later.
Articles 1–20