J. Droppo

发表

1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs

Dong Yu, Gang Li, Jasha Droppo, 2014, INTERSPEECH.

On parallelizability of stochastic gradient descent for speech DNNS

Dong Yu, Gang Li, Jasha Droppo, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An introduction to computational networks and the computational network toolkit (invited talk)

Geoffrey Zweig, Kaisheng Yao, Dong Yu, 2014, INTERSPEECH.

Direct filtering for air- and bone-conductive microphones

Zicheng Liu, Zhengyou Zhang, Alex Acero, 2004, IEEE 6th Workshop on Multimedia Signal Processing, 2004..

Toward Human Parity in Conversational Speech Recognition

Geoffrey Zweig, Andreas Stolcke, Dong Yu, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Deep bi-directional recurrent networks over spectral windows

Geoffrey Zweig, Andreas Stolcke, Dong Yu, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Noise Adaptive Training for Robust Automatic Speech Recognition

Alex Acero, Jasha Droppo, Ozlem Kalinli, 2010, IEEE Transactions on Audio, Speech, and Language Processing.

Analysis and comparison of two speech feature extraction/compensation algorithms

Li Deng, Alex Acero, Jian Wu, 2005, IEEE Signal Processing Letters.

Enhancement of log Mel power spectra of speech using a phase-sensitive model of the acoustic environment and sequential estimation of the corrupting noise

Li Deng, Alex Acero, Jasha Droppo, 2004, IEEE Transactions on Speech and Audio Processing.

Advances in all-neural speech recognition

Geoffrey Zweig, Andreas Stolcke, Chengzhu Yu, 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Phone sequence modeling with recurrent neural networks

Dong Yu, Jasha Droppo, Nicolas Boulanger-Lewandowski, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning

Jasha Droppo, Ritwik Giri, Dong Yu, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech enhancement using a pitch predictive model

Alex Acero, Jasha Droppo, Luis Buera, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Multi-task learning in deep neural networks for improved phoneme recognition

Jasha Droppo, Michael L. Seltzer, J. Droppo, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Towards a non-parametric acoustic model: an acoustic decision tree for observation probability calculation

Alex Acero, Jasha Droppo, Yu-Hsiang Bosco Chiu, 2008, INTERSPEECH.

Robust bandwidth extension of noise-corrupted narrowband speech

Alex Acero, Jasha Droppo, Michael L. Seltzer, 2005, INTERSPEECH.

Single-channel mixed speech recognition using deep neural networks

Dong Yu, Chao Weng, Jasha Droppo, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Context dependent phonetic string edit distance for automatic speech recognition

Alex Acero, Jasha Droppo, J. Droppo, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

A noise-robust ASR front-end using Wiener filter constructed from MMSE estimation of clean speech and noise

Jasha Droppo, Jian Wu, Li Deng, 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

Detection of Lexical Stress Errors in Non-native (L2) English with Data Augmentation and Attention pdf

Bozena Kostek, Thomas Drugman, Jasha Droppo, 2020, Interspeech.

Distributed speech processing in miPad's multimodal user interface

Li Deng, Alex Acero, Xuedong Huang, 2002, IEEE Trans. Speech Audio Process..

Exploiting variances in robust feature extraction based on a parametric model of speech distortion

Li Deng, Alex Acero, Jasha Droppo, 2002, INTERSPEECH.

Air- and bone-conductive integrated microphones for robust speech detection and enhancement

Xuedong Huang, Jasha Droppo, Zhengyou Zhang, 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

A comparison of three non-linear observation models for noisy speech features

Li Deng, Alex Acero, Jasha Droppo, 2003, INTERSPEECH.

Suppression Rule for Speech Recognition Friendly Noise Suppressors

Jasha Droppo, Ivan Tashev, Alex Acero, 2006 .

Evaluation of the SPLICE algorithm on the Aurora2 database

Li Deng, Alex Acero, Jasha Droppo, 2001, INTERSPEECH.

The Microsoft 2017 Conversational Speech Recognition System

Andreas Stolcke, Xuedong Huang, L. Wu, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Estimating cepstrum of speech under the presence of noise using a joint prior of static and dynamic features

Li Deng, Alex Acero, Jasha Droppo, 2004, IEEE Transactions on Speech and Audio Processing.

Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion

Li Deng, Alex Acero, Jasha Droppo, 2005, IEEE Transactions on Speech and Audio Processing.

Optimizing time-frequency distributions for automatic classification

Jasha Droppo, Jack McLaughlin, Les Atlas, 1997, Optics & Photonics.

Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition

Li Deng, Alex Acero, Jasha Droppo, 2003, IEEE Trans. Speech Audio Process..

MiPad: a multimodal interaction prototype

Li Deng, Joshua Goodman, Alex Acero, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

High-performance robust speech recognition using stereo training data

Li Deng, Alex Acero, Xuedong Huang, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Robust Speech Recognition Using a Cepstral Minimum-Mean-Square-Error-Motivated Noise Suppressor

Yifan Gong, Dong Yu, Li Deng, 2008, IEEE Transactions on Audio, Speech, and Language Processing.

Evaluation of SPLICE on the Aurora 2 and 3 tasks

Li Deng, Alex Acero, Jasha Droppo, 2002, INTERSPEECH.

Recursive noise estimation using iterative stochastic approximation for stereo-based robust speech recognition

Jasha Droppo, Li Deng, Alejandro Acero, 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

Speech and Language Processing for Multimodal Human-Computer Interaction

Li Deng, Alex Acero, Xuedong Huang, 2004, J. VLSI Signal Process..

Leakage model and teeth clack removal for air- and bone-conductive integrated microphones

Zicheng Liu, Zhengyou Zhang, Alex Acero, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Deep Convolutional Neural Networks with Layer-Wise Context Expansion and Attention

Geoffrey Zweig, Andreas Stolcke, Jinyu Li, 2016, INTERSPEECH.

Multi-sensory microphones for robust speech detection, enhancement and recognition

Zicheng Liu, Li Deng, Zhengyou Zhang, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Robust design of wideband loudspeaker arrays

Alex Acero, Jasha Droppo, Ivan Tashev, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Comparing Human and Machine Errors in Conversational Speech Transcription pdf

Andreas Stolcke, Jasha Droppo, J. Droppo, 2017, INTERSPEECH.

Robust speech recognition using cepstral minimum-mean-square-error noise suppressor

Yifan Gong, Dong Yu, Alex Acero, 2008 .

ReLU, Sigmoid, Tanh, Log, Cos, Dropout, Negate, Softmax, LogSoftmax, SumElements, RowSlice, RowStack, Scale, Times, DiagTimes, Plus, Minus, ElementTimes, KhatriRaoProd- uct, Reshape traInIng crIterIa SquareError, CrossEntropyWithSoftmax, ClassificationError, ClassBasedCrossEntropyWith- SoftMax, GMML

Clément Farabet, Koray Kavukcuoglu, Ronan Collobert, 2015 .

Speech and Language Processing for Multimodal Human-Computer Interaction (Invited Article)

Alex Acero, Li Deng, Xuedong Huang, 2004 .

Improved Representation Learning For Acoustic Event Classification Using Tree-Structured Ontology

J. Droppo, Chao Ching Wang, Q. Zhang, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Parallelizing WFST Speech Decoders (Poster)

Geoffrey Zweig, Jasha Droppo, Todd Mytkowicz, 2016 .

Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation

J. Droppo, A. Stolcke, R. Maas, 2022, INTERSPEECH.

ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale

Anit Kumar Sahu, J. Droppo, A. Rastrow, 2022, KDD.

The Microsoft 2017 Conversational Speech Recognition System [Technical Report]

Andreas Stolcke, Xuedong Huang, Jasha Droppo, 2017 .

Wav2vec-C: A Self-supervised Model for Speech Representation Learning pdf

Andreas Stolcke, Che-Wei Huang, Sri Harish Reddy Mallidi, 2021, Interspeech.

Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech

J. Droppo, A. Stolcke, Chengzhu Yu, 2022, ArXiv.

Achieving Human Parity in Conversational Speech Recognition pdf

Geoffrey Zweig, Andreas Stolcke, Dong Yu, 2016, ArXiv.

Improving Fairness in Speaker Verification via Group-Adapted Fusion Network

J. Droppo, A. Stolcke, Eunjung Han, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition

Andreas Stolcke, Roland Maas, Maarten Van Segbroeck, 2020, INTERSPEECH.

SynthASR: Unlocking Synthetic Data for Speech Recognition pdf

Roland Maas, Jasha Droppo, Wei Yang, 2021, Interspeech.

Exploring the application of synthetic audio in training keyword spotters

Jasha Droppo, Roberto Barra-Chicote, Peng Liu, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Single-channel Speech Extraction Using Speaker Inventory and Attention Network

Zhuo Chen, Yifan Gong, Hakan Erdogan, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition pdf

Sri Harish Reddy Mallidi, Roland Maas, Jasha Droppo, 2021, ArXiv.

Joint ASR and Language Identification Using RNN-T: An Efficient Approach to Dynamic Language Switching

Andreas Stolcke, Athanasios Mouchtaris, Roland Maas, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DO as I Mean, Not as I Say: Sequence Loss Training for Spoken Language Understanding

Andreas Stolcke, Ariya Rastrow, Jasha Droppo, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Progressive Joint Modeling in Unsupervised Single-Channel Overlapped Speech Recognition

Jinyu Li, Jasha Droppo, Zhehuai Chen, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Improving multi-speaker TTS prosody variance with a residual encoder and normalizing flows pdf

Jasha Droppo, Roberto Barra-Chicote, Grzegorz Beringer, 2021, Interspeech.

CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition pdf

Athanasios Mouchtaris, Jasha Droppo, Rupak Vignesh Swaminathan, 2021, Interspeech.

Top-Down Attention in End-to-End Spoken Language Understanding

Alejandro Mottini, Jasha Droppo, Erran L. Li, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning Methods in Multilingual Speech Recognition

Hui Lin, Dong Yu, Li Deng, 2008, NIPS 2008.

Evaluating the Vulnerability of End-to-End Automatic Speech Recognition Models to Membership Inference Attacks

J. Droppo, A. Mouchtaris, Muhammad A. Shah, 2021, Interspeech.

Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End pdf

Andreas Stolcke, Ariya Rastrow, Jasha Droppo, 2021, Interspeech.

Parallelizing WFST speech decoders

Geoffrey Zweig, Jasha Droppo, Todd Mytkowicz, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Scaling Effect of Self-Supervised Speech Models

Jasha Droppo, Oguz H. Elibol, Ruirui Li, 2021, Interspeech.

Acoustic-to-word model without OOV

Yifan Gong, Jinyu Li, Jasha Droppo, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

The microsoft 2016 conversational speech recognition system

Geoffrey Zweig, Andreas Stolcke, Dong Yu, 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Sequence Modeling in Unsupervised Single-Channel Overlapped Speech Recognition

Jasha Droppo, Zhehuai Chen, J. Droppo, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Federated Self-Learning with Weak Supervision for Speech Recognition

J. Droppo, A. Rastrow, Milind Rao, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Incremental Bayes learning with prior evolution for tracking nonstationary noise statistics from noisy speech data

Li Deng, Alex Acero, Jasha Droppo, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

A Bayesian approach to speech feature enhancement using the dynamic cepstral prior

Li Deng, Alex Acero, Jasha Droppo, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Investigation of Training Label Error Impact on RNN-T pdf

I-Fan Chen, Jasha Droppo, Brian King, 2021, ArXiv.

Exploiting LSTM structure in deep neural networks for speech recognition

Jasha Droppo, Tianxing He, J. Droppo, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Noise robust speech recognition with a switching linear dynamic model

Alex Acero, Jasha Droppo, J. Droppo, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Uncertainty decoding with SPLICE for noise robust speech recognition

Li Deng, Alex Acero, Jasha Droppo, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Scaling Laws for Acoustic Models pdf

Jasha Droppo, Oguz H. Elibol, Oguz Elibol, 2021, Interspeech.

Diffusion-based accent modelling in speech synthesis

J. Droppo, K. Deja, Marius Cotescu, 2023, INTERSPEECH.

Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition

J. Droppo, R. Maas, Minhua Wu, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Robust Speech Recognition Using a Cepstral Minimum-Mean-Square-Error-Motivated

L. Deng, Dong Yu, J. Droppo, 2008 .

Self-stabilized deep neural network

Jasha Droppo, Pegah Ghahremani, J. Droppo, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).