Kartik Audhkhasi
Kartik Audhkhasi
IBM Research AI
Verifierad e-postadress på us.ibm.com - Startsida
TitelCiteras avÅr
English conversational telephone speech recognition by humans and machines
G Saon, G Kurata, T Sercu, K Audhkhasi, S Thomas, D Dimitriadis, X Cui, ...
arXiv preprint arXiv:1703.02136, 2017
1812017
Direct acoustics-to-word models for english conversational speech recognition
K Audhkhasi, B Ramabhadran, G Saon, M Picheny, D Nahamoo
arXiv preprint arXiv:1703.07754, 2017
792017
Applying machine learning to facilitate autism diagnostics: pitfalls and promises
D Bone, MS Goodwin, MP Black, CC Lee, K Audhkhasi, S Narayanan
Journal of autism and developmental disorders 45 (5), 1121-1136, 2015
742015
Noise-enhanced convolutional neural networks
K Audhkhasi, O Osoba, B Kosko
Neural Networks 78, 15-23, 2016
642016
Multilingual representations for low resource speech recognition and keyword search
J Cui, B Kingsbury, B Ramabhadran, A Sethy, K Audhkhasi, Z Tüske, ...
Proc. ASRU, 2015
582015
Building competitive direct acoustics-to-word models for english conversational speech recognition
K Audhkhasi, B Kingsbury, B Ramabhadran, G Saon, M Picheny
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
552018
Formant-based technique for automatic filled-pause detection in spontaneous spoken English
K Audhkhasi, K Kandhway, OD Deshmukh, A Verma
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
542009
Which ASR should I choose for my dialogue system?
F Morbini, K Audhkhasi, K Sagae, R Artstein, D Can, P Georgiou, ...
SIGDIAL 2013, 2013
472013
Automatic evaluation of spoken fluency
K Audhkhasi, OD Deshmukh, K Kandhway, A Verma
US Patent 8,457,967, 2013
422013
A globally-variant locally-constant model for fusion of labels from multiple diverse experts without using reference labels
K Audhkhasi, S Narayanan
IEEE transactions on pattern analysis and machine intelligence 35 (4), 769-783, 2012
382012
End-to-End ASR-free Keyword Search from Speech
K Audhkhasi, A Rosenberg, A Sethy, B Ramabhadran, B Kingsbury
arXiv preprint arXiv:1701.04313, 2017
372017
Invariant representations for noisy speech recognition
D Serdyuk, K Audhkhasi, P Brakel, B Ramabhadran, S Thomas, Y Bengio
arXiv preprint arXiv:1612.01928, 2016
372016
Paralinguistic event detection from speech using probabilistic time-series smoothing and masking
R Gupta, K Audhkhasi, S Lee, S Narayanan
Proc. Interspeech, 2013
352013
Keyword search using modified minimum edit distance measure
K Audhkhasi, A Verma
2007 IEEE International Conference on Acoustics, Speech and Signal …, 2007
302007
Noise benefits in backpropagation and deep bidirectional pre-training
K Audhkhasi, O Osoba, B Kosko
The 2013 International Joint Conference on Neural Networks (IJCNN), 1-8, 2013
282013
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
262017
Efficient one-vs-one kernel ridge regression for speech recognition
J Chen, L Wu, K Audhkhasi, B Kingsbury, B Ramabhadrari
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
252016
Theoretical analysis of diversity in an ensemble of automatic speech recognition systems
K Audhkhasi, AM Zavou, PG Georgiou, SS Narayanan
IEEE/ACM Transactions on Audio, Speech, and Language Processing 22 (3), 711-726, 2014
222014
Accurate transcription of broadcast news speech using multiple noisy transcribers and unsupervised reliability metrics
K Audhkhasi, P Georgiou, SS Narayanan
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011
222011
Reliability-weighted acoustic model adaptation using crowd sourced transcriptions
K Audhkhasi, P Georgiou, S Narayanan
Proc. Interspeech2011, Florence, 2011
212011
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20