2 citations · 2 across the 6 of their papers we have counts for
7 papers
Decaf: A privacy preserving speech codec using speaker disentanglement and canonical voice conversion
Md Shakhrul Iman Siam, Dushyant Sharma, Stanislav Yu. Kruchinin +1
We present DECAF, a privacy preserving neural speech codec that obfuscates a speaker's voice while preserving linguistic content while maintaining automatic speech recognition (ASR…
XANE Background Acoustic Embeddings: Ablation and Clustering Analysis
Dushyant Sharma, James Fosburgh, Sri Harsha Dumpala +3
We explore the recently proposed explainable acoustic neural embedding~(XANE) system that models the background acoustics of a speech signal in a non-intrusive manner. The XANE emb…
XANE: eXplainable Acoustic Neural Embeddings
Sri Harsha Dumpala, Dushyant Sharma, Chandramouli Shama Sastri +3
We present a novel method for extracting neural embeddings that model the background acoustics of a speech signal. The extracted embeddings are used to estimate specific parameters…
Spatial Processing Front-End For Distant ASR Exploiting Self-Attention Channel Combinator
Dushyant Sharma, Rong Gong, James Fosburgh +3
We present a novel multi-channel front-end based on channel shortening with theWeighted Prediction Error (WPE) method followed by a fixed MVDR beamformer used in combination with a…
ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization
Marco Gaudesi, Felix Weninger, Dushyant Sharma +1
End-to-end (E2E) multi-channel ASR systems show state-of-the-art performance in far-field ASR tasks by joint training of a multi-channel front-end along with the ASR model. The mai…
Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-field Speech Recognition
Rong Gong, Carl Quillen, Dushyant Sharma +3
When a sufficiently large far-field training data is presented, jointly optimizing a multichannel frontend and an end-to-end (E2E) Automatic Speech Recognition (ASR) backend shows…
Evaluating the Non-Intrusive Room Acoustics Algorithm with the ACE Challenge
Pablo Peso Parada, Dushyant Sharma, Toon van Waterschoot +1
We present a single channel data driven method for non-intrusive estimation of full-band reverberation time and full-band direct-to-reverberant ratio. The method extracts a number…