activity
20162025
most citedMulti-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition

15 citations · 16 across the 5 of their papers we have counts for

collaborators

5 papers

cs.SD2025

Unifying Streaming and Non-streaming Zipformer-based ASR

Bidisha Sharma, Karthik Pandia Durai, Shankar Venkatesan +4

There has been increasing interest in unifying streaming and non-streaming automatic speech recognition (ASR) models to reduce development, training, and deployment costs. We prese…

cs.CL201715 cited

Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition

Abhinav Thanda, Shankar M Venkatesan

Multi-task learning (MTL) involves the simultaneous training of two or more related tasks over shared representations. In this work, we apply MTL to audio-visual automatic speech r…

cs.CV20161 cited

Audio Visual Speech Recognition using Deep Recurrent Neural Networks

Abhinav Thanda, Shankar M Venkatesan

In this work, we propose a training algorithm for an audio-visual automatic speech recognition (AV-ASR) system using deep recurrent neural network (RNN).First, we train a deep RNN…

math.CO2016

Polynomials and Second Order Linear Recurrences

Soumyabrata Pal, Shankar M. Venkatesan

One of the most interesting results of the last century was the proof completed by Matijasevich that computably enumerable sets are precisely the diophantine sets [MRDP Theorem, 9]…

math.CO2016

Tight lower bounds for connected queen domination problems on the chessboard

Sneha S. Venkatesan, S. M. Venkatesan

1. We first show a lower bound of 2N/3-1 for the connected minimum queen domination (or cover) problem on the NXN chessboard - the upper bound is only 2 higher at most and is easy…