Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Venkatesan, Shankar M."'
People capture memorable images of events and exhibits that are often occluded by a wire mesh loosely termed as fence. Recent works in removing fence have limited performance due to the difficulty in initial fence segmentation. This work aims to accu
Externí odkaz:
http://arxiv.org/abs/2007.01724
Autor:
Aralikatti, Rohith, Roy, Sharad, Thanda, Abhinav, Margam, Dilip Kumar, Kandala, Pujitha Appan, Sharma, Tanay, Venkatesan, Shankar M
Under noisy conditions, speech recognition systems suffer from high Word Error Rates (WER). In such cases, information from the visual modality comprising the speaker lip movements can help improve the performance. In this work, we propose novel meth
Externí odkaz:
http://arxiv.org/abs/2001.10832
Autor:
Margam, Dilip Kumar, Aralikatti, Rohith, Sharma, Tanay, Thanda, Abhinav, K, Pujitha A, Roy, Sharad, Venkatesan, Shankar M
In recent years, deep learning based machine lipreading has gained prominence. To this end, several architectures such as LipNet, LCANet and others have been proposed which perform extremely well compared to traditional lipreading DNN-HMM hybrid syst
Externí odkaz:
http://arxiv.org/abs/1906.12170
This paper demonstrates two novel methods to estimate the global SNR of speech signals. In both methods, Deep Neural Network-Hidden Markov Model (DNN-HMM) acoustic model used in speech recognition systems is leveraged for the additional task of SNR e
Externí odkaz:
http://arxiv.org/abs/1804.04353
Autor:
Thanda, Abhinav, Venkatesan, Shankar M
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 recognition(AV-ASR). Our primary task is to learn a mapping between aud
Externí odkaz:
http://arxiv.org/abs/1701.02477
Autor:
Thanda, Abhinav, Venkatesan, Shankar M
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 acoustic model with a Connectionist Temporal Classification (CTC) obje
Externí odkaz:
http://arxiv.org/abs/1611.02879
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], thus settling, based on previously developed machinery, Hilbert's qu
Externí odkaz:
http://arxiv.org/abs/1608.06404
Wall published a paper in 1960 on the Fibonacci sequence where he derived many results concerning the period and prime power divisibility modulo m. His periodicity results have been generalized to second order linear recurrences. Here we study the se
Externí odkaz:
http://arxiv.org/abs/1509.03794
Publikováno v:
Acta Informatica. 1997, Vol. 34 Issue 3, p231. 13p.
Publikováno v:
Proceedings of International Conference on Computer Vision & Image Processing; 2017, p629-641, 13p