Ehsan Variani
Ehsan Variani
Verified email at - Homepage
Cited by
Cited by
Deep neural networks for small footprint text-dependent speaker verification
E Variani, X Lei, E McDermott, IL Moreno, J Gonzalez-Dominguez
2014 IEEE international conference on acoustics, speech and signal …, 2014
Multichannel signal processing with deep neural networks for automatic speech recognition
TN Sainath, RJ Weiss, KW Wilson, B Li, A Narayanan, E Variani, ...
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (5), 965-979, 2017
Acoustic Modeling for Google Home.
B Li, TN Sainath, A Narayanan, J Caroselli, M Bacchiani, A Misra, ...
Interspeech, 399-403, 2017
Hybrid autoregressive transducer (hat)
E Variani, D Rybach, C Allauzen, M Riley
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
A density ratio approach to language model fusion in end-to-end automatic speech recognition
E McDermott, H Sak, E Variani
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
A Gaussian mixture model layer jointly optimized with discriminative features within a deep neural network architecture
E Variani, E McDermott, G Heigold
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
Mean temporal distance: Predicting ASR error from temporal properties of speech signal
H Hermansky, E Variani, V Peddinti
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
Cascaded encoders for unifying streaming and non-streaming ASR
A Narayanan, TN Sainath, R Pang, J Yu, CC Chiu, R Prabhavalkar, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
Speaker verification using neural networks
X Lei, E McDermott, E Variani, IL Moreno
US Patent 9,401,148, 2016
Complex linear projection (CLP): A discriminative approach to joint feature extraction and acoustic modeling
E Variani, TN Sainath, I Shafran, M Bacchiani
An efficient streaming non-recurrent on-device end-to-end model with improvements to rare-word modeling
TN Sainath, YR He, A Narayanan, R Botros, R Pang, DJ Rybach, ...
End-to-end training of acoustic models for large vocabulary continuous speech recognition with tensorflow
E Variani, T Bagby, E McDermott, M Bacchiani
Enhanced multi-channel acoustic models
E Variani, KW Wilson, RJ Weiss, TN Sainath, A Narayanan
US Patent 10,224,058, 2019
Complex linear projection for acoustic modeling
S Bengio, M Visontai, CWG Thornton, MAU Bacchiani, TN Sainath, ...
US Patent 10,140,980, 2018
Multi-stream recognition of noisy speech with performance monitoring.
E Variani, F Li, H Hermansky
Interspeech, 2978-2981, 2013
Reducing the computational complexity of multimicrophone acoustic models with integrated feature extraction
TN Sainath, A Narayanan, RJ Weiss, E Variani, KW Wilson, M Bacchiani, ...
Raw multichannel processing using deep neural networks
TN Sainath, RJ Weiss, KW Wilson, A Narayanan, M Bacchiani, B Li, ...
New Era for Robust Speech Recognition: Exploiting Deep Learning, 105-133, 2017
Efficient implementation of the room simulator for training deep neural network acoustic models
C Kim, E Variani, A Narayanan, M Bacchiani
arXiv preprint arXiv:1712.03439, 2017
Neural oracle search on n-best hypotheses
E Variani, T Chen, J Apfel, B Ramabhadran, S Lee, P Moreno
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
Modular hybrid autoregressive transducer
Z Meng, T Chen, R Prabhavalkar, Y Zhang, G Wang, K Audhkhasi, ...
2022 IEEE Spoken Language Technology Workshop (SLT), 197-204, 2023
The system can't perform the operation now. Try again later.
Articles 1–20