Author Info
Name
Affiliation
Papers
S. ASWIN SHANMUGAM
Indian Inst Technol, Madras, Tamil Nadu, India
12
Collaborators
Citations 
PageRank 
49
7
4.21
Referers 
Referees 
References 
33
65
27
Title
Citations
PageRank
Year
Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition10.372022
Espnet-Se: End-To-End Speech Enhancement And Separation Toolkit Designed For Asr Integration00.342021
DIRECTIONAL ASR: A NEW PARADIGM FOR E2E MULTI-SPEAKER SPEECH RECOGNITION WITH SOURCE LOCALIZATION00.342021
An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition20.362021
End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming10.352020
Significance of Spectral Cues in Automatic Speech Segmentation for Indian Language Speech Synthesizers20.422020
End-to-End ASR with Adaptive Span Self-Attention.00.342020
Attention-based ASR with Lightweight and Dynamic Convolutions00.342020
Generalized Weighted-Prediction-Error Dereverberation with Varying Source Priors For Reverberant Speech Recognition00.342019
Dry, Focus, and Transcribe: End-to-End Integration of Dereverberation, Beamforming, and ASR.00.342019
Speech Enhancement Using End-to-End Speech Recognition Objectives10.352019
Tbt (Toolkit To Build Tts): A High Performance Framework To Build Multiple Language Hts Voice00.342017