Jasha Droppo

Orcid: 0000-0001-6097-0090

Affiliations:
  • Microsoft Research


According to our database1, Jasha Droppo authored at least 101 papers between 2001 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
LightLT: A Lightweight Representation Quantization Framework for Long-Tail Data.
Proceedings of the 40th IEEE International Conference on Data Engineering, 2024

2023
Federated Representation Learning for Automatic Speech Recognition.
CoRR, 2023

Diffusion-based accent modelling in speech synthesis.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Federated Self-Learning with Weak Supervision for Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2023

2022
Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech.
CoRR, 2022

Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition.
Proceedings of the IEEE Spoken Language Technology Workshop, 2022

ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale.
Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 2022

Do You Listen with one or two Microphones? A Unified ASR Model for Single and Multi-Channel Audio.
Proceedings of the 17th International Workshop on Acoustic Signal Enhancement, 2022

Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Adversarial Reweighting for Speaker Verification Fairness.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Improved Representation Learning For Acoustic Event Classification Using Tree-Structured Ontology.
Proceedings of the IEEE International Conference on Acoustics, 2022

Improving Fairness in Speaker Verification via Group-Adapted Fusion Network.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
Investigation of Training Label Error Impact on RNN-T.
CoRR, 2021

Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition.
CoRR, 2021

Improving Multi-Speaker TTS Prosody Variance with a Residual Encoder and Normalizing Flows.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

CoDERT: Distilling Encoder Representations with Co-Learning for Transducer-Based Speech Recognition.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Evaluating the Vulnerability of End-to-End Automatic Speech Recognition Models to Membership Inference Attacks.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

wav2vec-C: A Self-Supervised Model for Speech Representation Learning.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Scaling Effect of Self-Supervised Speech Models.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

SynthASR: Unlocking Synthetic Data for Speech Recognition.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Scaling Laws for Acoustic Models.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Exploring the application of synthetic audio in training keyword spotters.
Proceedings of the IEEE International Conference on Acoustics, 2021

DO as I Mean, Not as I Say: Sequence Loss Training for Spoken Language Understanding.
Proceedings of the IEEE International Conference on Acoustics, 2021

Joint ASR and Language Identification Using RNN-T: An Efficient Approach to Dynamic Language Switching.
Proceedings of the IEEE International Conference on Acoustics, 2021

Top-Down Attention in End-to-End Spoken Language Understanding.
Proceedings of the IEEE International Conference on Acoustics, 2021

2020
Efficient Minimum Word Error Rate Training of RNN-Transducer for End-to-End Speech Recognition.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

2019
Single-channel Speech Extraction Using Speaker Inventory and Attention Network.
Proceedings of the IEEE International Conference on Acoustics, 2019

2018
Progressive Joint Modeling in Unsupervised Single-Channel Overlapped Speech Recognition.
IEEE ACM Trans. Audio Speech Lang. Process., 2018

The Microsoft 2017 Conversational Speech Recognition System.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Sequence Modeling in Unsupervised Single-Channel Overlapped Speech Recognition.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
Toward Human Parity in Conversational Speech Recognition.
IEEE ACM Trans. Audio Speech Lang. Process., 2017

Comparing Human and Machine Errors in Conversational Speech Transcription.
Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Advances in all-neural speech recognition.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

The microsoft 2016 conversational speech recognition system.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Acoustic-to-word model without OOV.
Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2016
Achieving Human Parity in Conversational Speech Recognition.
CoRR, 2016

On training bi-directional neural network language model with noise contrastive estimation.
Proceedings of the 10th International Symposium on Chinese Spoken Language Processing, 2016

Deep Convolutional Neural Networks with Layer-Wise Context Expansion and Attention.
Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Parallelizing WFST speech decoders.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Exploiting LSTM structure in deep neural networks for speech recognition.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Linearly augmented deep neural network.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Self-stabilized deep neural network.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015
Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition.
IEEE ACM Trans. Audio Speech Lang. Process., 2015

Speech recognition with prediction-adaptation-correction recurrent neural networks.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Deep bi-directional recurrent networks over spectral windows.
Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014
An introduction to computational networks and the computational network toolkit (invited talk).
Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs.
Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Single-channel mixed speech recognition using deep neural networks.
Proceedings of the IEEE International Conference on Acoustics, 2014

On parallelizability of stochastic gradient descent for speech DNNS.
Proceedings of the IEEE International Conference on Acoustics, 2014

Phone sequence modeling with recurrent neural networks.
Proceedings of the IEEE International Conference on Acoustics, 2014

2013
Multi-task learning in deep neural networks for improved phoneme recognition.
Proceedings of the IEEE International Conference on Acoustics, 2013

2012
A chunk-based phonetic score for mobile voice search.
Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Feature Compensation.
Proceedings of the Techniques for Noise Robustness in Automatic Speech Recognition, 2012

2011
Automatically Optimizing Utterance Classification Performance without Human in the Loop.
Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Learning non-parametric models of pronunciation.
Proceedings of the IEEE International Conference on Acoustics, 2011

Joint encoding of the waveform and speech recognition features using a transform codec.
Proceedings of the IEEE International Conference on Acoustics, 2011

2010
Noise Adaptive Training for Robust Automatic Speech Recognition.
IEEE Trans. Speech Audio Process., 2010

Spontaneous Mandarin speech understanding using Utterance Classification: A case study.
Proceedings of the 7th International Symposium on Chinese Spoken Language Processing, 2010

Continuous speech recognition with a TF-IDF acoustic model.
Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Information retrieval methods for automatic speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2010

Context dependent phonetic string edit distance for automatic speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2010

2009
Experimenting with a global decision tree for state clustering in automatic speech recognition systems.
Proceedings of the IEEE International Conference on Acoustics, 2009

2008
Robust Speech Recognition Using a Cepstral Minimum-Mean-Square-Error-Motivated Noise Suppressor.
IEEE Trans. Speech Audio Process., 2008

Towards a non-parametric acoustic model: an acoustic decision tree for observation probability calculation.
Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

A minimum-mean-square-error noise reduction algorithm on Mel-frequency cepstra for robust speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2008

Robust design of wideband loudspeaker arrays.
Proceedings of the IEEE International Conference on Acoustics, 2008

Speech enhancement using a pitch predictive model.
Proceedings of the IEEE International Conference on Acoustics, 2008

2007
A fine pitch model for speech.
Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Maximum Entropy Confidence Estimation for Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2007

2006
Joint Discriminative Front End and Back End Training for Improved Speech Recognition Accuracy.
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005
Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion.
IEEE Trans. Speech Audio Process., 2005

Analysis and comparison of two speech feature extraction/compensation algorithms.
IEEE Signal Process. Lett., 2005

A graphical model for multi-sensory speech processing in air-and-bone conductive microphones.
Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Robust bandwidth extension of noise-corrupted narrowband speech.
Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Maximum mutual information SPLICE transform for seen and unseen conditions.
Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Leakage Model and Teeth Clack Removal for Air- and Bone-Conductive Integrated Microphones.
Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004
Speech and Language Processing for Multimodal Human-Computer Interaction.
J. VLSI Signal Process., 2004

Estimating cepstrum of speech under the presence of noise using a joint prior of static and dynamic features.
IEEE Trans. Speech Audio Process., 2004

Enhancement of log Mel power spectra of speech using a phase-sensitive model of the acoustic environment and sequential estimation of the corrupting noise.
IEEE Trans. Speech Audio Process., 2004

Direct filtering for air- and bone-conductive microphones.
Proceedings of the IEEE 6th Workshop on Multimedia Signal Processing, 2004

Multi-sensory microphones for robust speech detection, enhancement and recognition.
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Noise robust speech recognition with a switching linear dynamic model.
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003
Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition.
IEEE Trans. Speech Audio Process., 2003

A harmonic-model-based front end for robust speech recognition.
Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

A comparison of three non-linear observation models for noisy speech features.
Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Incremental Bayes learning with prior evolution for tracking nonstationary noise statistics from noisy speech data.
Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002
Distributed speech processing in miPad's multimodal user interface.
IEEE Trans. Speech Audio Process., 2002

Evaluation of SPLICE on the Aurora 2 and 3 tasks.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Noise from corrupted speech log mel-spectral energies.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Exploiting variances in robust feature extraction based on a parametric model of speech distortion.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Sequential MAP noise estimation and a phase-sensitive model of the acoustic environment.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Uncertainty decoding with SPLICE for noise robust speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2002

A Bayesian approach to speech feature enhancement using the dynamic cepstral prior.
Proceedings of the IEEE International Conference on Acoustics, 2002

A speech-centric perspective for human-computer interface.
Proceedings of the IEEE 5th Workshop on Multimedia Signal Processing, 2002

2001
Evaluation of the SPLICE algorithm on the Aurora2 database.
Proceedings of the EUROSPEECH 2001 Scandinavia, 2001


Efficient on-line acoustic environment estimation for FCDCN in a continuous speech recognition system.
Proceedings of the IEEE International Conference on Acoustics, 2001

High-performance robust speech recognition using stereo training data.
Proceedings of the IEEE International Conference on Acoustics, 2001


  Loading...