Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Venkata Subrahmanyam Chandra Sekhar Chebiyyam"'
Publikováno v:
INTERSPEECH
Publikováno v:
INTERSPEECH
Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal attention th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7d6d3e2cffd26e90d8c830aa1d1bfef
http://arxiv.org/abs/1901.08608
http://arxiv.org/abs/1901.08608
Autor:
Daniel J. Sinder, Jeremie Lecomte, Benjamin Schubert, Duminda A. Dewasurendra, Atti Venkatraman S, Venkata Subrahmanyam Chandra Sekhar Chebiyyam, Subasingha Shaminda Subasingha, Lei Miao, Vivek Rajendran, Imre Varga, Venkatesh Krishnan, Xingtao Zhang
Publikováno v:
ICASSP
A highly error resilient mode of the newly standardized 3GPP EVS speech codec is described. Compared to the AMR-WB codec and other conversational codecs, the EVS channel aware mode offers significantly improved error resilience in voice communication
Autor:
Duminda A. Dewasurendra, Daniel J. Sinder, Volodya Grancharov, Venkata Subrahmanyam Chandra Sekhar Chebiyyam, Subasingha Shaminda Subasingha, Harald Pobloth, Atti Venkatraman S, Jon Gibbs, Vivek Rajendran, Imre Varga, Lei Miao, Venkatesh Krishnan
Publikováno v:
ICASSP
This paper describes the time-domain bandwidth extension (TBE) framework employed to code wideband and super-wideband speech in the newly standardized 3GPP EVS codec. The TBE algorithm uses a nonlinear harmonic modeling technique that incorporates pr