← Authors

Arun Narayanan

21 papers · 2016–2024 · 1 conference · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (13) πŸ—ΊοΈ Taxonomy Completionist (26) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (8) 🧭 Keyword Pioneer 🏠 Conference Loyalist (21) πŸ† Keyword Champion (2) πŸ‘₯ Mega-Team (20) πŸ—ƒοΈ Keyword Collector (74) πŸš€ Conference Pioneer πŸ’Ž Century Club (21) πŸ”₯ Unstoppable (5) ⚑ Prolific Year (5)

Conferences

INTERSPEECH (21)

Top co-authors

Michiel Bacchiani (6) Ananya Misra (5) Tara N. Sainath (5) Ehsan Variani (4) Khe Chai Sim (4) Izhak Shafran (3) Sankaran Panchapagesan (3) Bo Li (3) Chanwoo Kim (3) Joe Caroselli (3)

Keywords

automatic speech recognition (11) speech enhancement (5) neural network (4) speech recognition (4) acoustic model (4) acoustic echo cancellation (3) acoustic modeling (2) data augmentation (2) speaker embedding (2) deep neural network (2) on-device speech recognition (2) word error rate (2) gradient clipping (2) end-to-end model (2) sequence training (2) streaming model (2) signal-to-noise ratio (1) speaker verification (1) domain adaptation (1) computational complexity (1)

Papers

Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping INTERSPEECH 2024
TfCleanformer: A streaming, array-agnostic, full- and sub-band modeling front-end for robust ASR INTERSPEECH 2024
Quantifying Unintended Memorization in BEST-RQ ASR Encoders INTERSPEECH 2024
On Training a Neural Residual Acoustic Echo Suppressor for Improved ASR INTERSPEECH 2023
SNRi Target Training for Joint Speech Enhancement and Recognition INTERSPEECH 2022
A universally-deployable ASR frontend for joint acoustic echo cancellation, speech enhancement, and voice separation INTERSPEECH 2022
Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition INTERSPEECH 2022
Extracting Targeted Training Data from ASR Models, and How to Mitigate It INTERSPEECH 2022
A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy INTERSPEECH 2022
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling INTERSPEECH 2021
A Comparison of Supervised and Unsupervised Pre-Training of End-to-End Models INTERSPEECH 2021
Personalized Keyphrase Detection Using Speaker and Environment Information INTERSPEECH 2021
Anti-Aliasing Regularization in Stacking Layers INTERSPEECH 2020
Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models INTERSPEECH 2018
Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition INTERSPEECH 2018
An Efficient Phone N-Gram Forward-Backward Computation Using Dense Matrix Multiplication INTERSPEECH 2017
Acoustic Modeling for Google Home INTERSPEECH 2017
Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home INTERSPEECH 2017
Adaptive Multichannel Dereverberation for Automatic Speech Recognition INTERSPEECH 2017
Annealed f-Smoothing as a Mechanism to Speed up Neural Network Training INTERSPEECH 2017
Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction INTERSPEECH 2016