Ehsan Variani

According to our database1, Ehsan Variani authored at least 33 papers between 2011 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
Last: Scalable Lattice-Based Speech Modelling in Jax.
Proceedings of the IEEE International Conference on Acoustics, 2023

Alignment Entropy Regularization.
Proceedings of the IEEE International Conference on Acoustics, 2023

JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2023

2022
Modular Hybrid Autoregressive Transducer.
Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Global Normalization for Streaming Speech Recognition in a Modular Framework.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Improving Rare Word Recognition with LM-aware MWER Training.
Proceedings of the Interspeech 2022, 2022

On Adaptive Weight Interpolation of the Hybrid Autoregressive Transducer.
Proceedings of the Interspeech 2022, 2022

UserLibri: A Dataset for ASR Personalization Using Only Text.
Proceedings of the Interspeech 2022, 2022

Multilingual Second-Pass Rescoring for Automatic Speech Recognition Systems.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

A Hybrid Seq-2-Seq ASR Design for On-Device and Server Applications.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Cascaded Encoders for Unifying Streaming and Non-Streaming ASR.
Proceedings of the IEEE International Conference on Acoustics, 2021

2020
Hybrid Autoregressive Transducer (HAT).
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Neural Oracle Search on N-BEST Hypotheses.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
West: Word Encoded Sequence Transducers.
Proceedings of the IEEE International Conference on Acoustics, 2019

A Density Ratio Approach to Language Model Fusion in End-to-End Automatic Speech Recognition.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018
Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models.
Proceedings of the Interspeech 2018, 2018

Sampled Connectionist Temporal Classification.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition.
IEEE ACM Trans. Audio Speech Lang. Process., 2017

End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow.
Proceedings of the Interspeech 2017, 2017


Raw Multichannel Processing Using Deep Neural Networks.
Proceedings of the New Era for Robust Speech Recognition, Exploiting Deep Learning., 2017

2016
Stream fusion for multi-stream automatic speech recognition.
Int. J. Speech Technol., 2016

Complex Linear Projection (CLP): A Discriminative Approach to Joint Feature Extraction and Acoustic Modeling.
Proceedings of the Interspeech 2016, 2016

Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction.
Proceedings of the Interspeech 2016, 2016

2015
Non-Adaptative Policies for 20 Questions Target Localization.
CoRR, 2015

NON-adaptive policies for 20 questions target localization.
Proceedings of the IEEE International Symposium on Information Theory, 2015

A Gaussian Mixture Model layer jointly optimized with discriminative features within a Deep Neural Network architecture.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014
Deep neural networks for small footprint text-dependent speaker verification.
Proceedings of the IEEE International Conference on Acoustics, 2014

2013
Multi-stream recognition of noisy speech with performance monitoring.
Proceedings of the INTERSPEECH 2013, 2013

Mean temporal distance: Predicting ASR error from temporal properties of speech signal.
Proceedings of the IEEE International Conference on Acoustics, 2013

2012
Estimating Classifier Performance in Unknown Noise.
Proceedings of the INTERSPEECH 2012, 2012

2011
VTLN in the MFCC Domain: Band-Limited versus Local Interpolation.
Proceedings of the INTERSPEECH 2011, 2011


  Loading...