Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Alexander H. Gruenstein"'
Autor:
Howard Nathan David, Rohit Prabhavalkar, Alexander H. Gruenstein, Alex Park, Turaj Zakizadeh Shabestary
Publikováno v:
ICASSP
We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs. Previous wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44e36f512e6a40e10cab66b4edd24353
https://doi.org/10.1109/icassp39728.2021.9413585
https://doi.org/10.1109/icassp39728.2021.9413585
Autor:
Sankaran Panchapagesan, Qiao Liang, Alexander H. Gruenstein, Yuan Shangguan, Chung-Cheng Chiu, Daniel S. Park
Publikováno v:
ICASSP
Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In this paper,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b1078dc6604ff83bbc3470a5cdf3293
Publikováno v:
ICASSP
This paper presents a novel dual-microphone speech enhancement algorithm to improve noise robustness of hotword (wake-word) detection as a special application of keyword spotting. It exploits two unique properties of hotwords: they are leading phrase
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::62605bfdc14bfe693175384863576837
https://doi.org/10.1109/icassp.2019.8682682
https://doi.org/10.1109/icassp.2019.8682682
Autor:
Anjuli Kannan, Khe Chai Sim, Qiao Liang, Tom Bagby, Yuan Shangguan, Yanzhang He, Rohit Prabhavalkar, Ruoming Pang, David Rybach, Golan Pundak, Ian McGraw, Deepti Bhatia, Yonghui Wu, Shuo-Yiin Chang, Bo Li, Ding Zhao, Kanishka Rao, Alexander H. Gruenstein, Tara N. Sainath, Raziel Alvarez
Publikováno v:
ICASSP
End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::577a7cd09af26dcf33fbed587348577f
https://doi.org/10.1109/icassp.2019.8682336
https://doi.org/10.1109/icassp.2019.8682336
Autor:
Francoise Beaufays, Pedro J. Moreno, Johan Schalkwyk, Michiel Bacchiani, Alexander H. Gruenstein, Heiga Zen, Trevor Strohman
Publikováno v:
New Era for Robust Speech Recognition ISBN: 9783319646794
New Era for Robust Speech Recognition, Exploiting Deep Learning
New Era for Robust Speech Recognition, Exploiting Deep Learning
Since the wide adoption of smartphones, speech as an input modality has developed from a science fiction dream to a widely accepted technology. The quality demand on this technology that allowed fueling this adoption is high and has been a continuous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e91de6266f5341a97cec48b6e13d41ed
https://doi.org/10.1007/978-3-319-64680-0_18
https://doi.org/10.1007/978-3-319-64680-0_18
Autor:
Raziel Alvarez, Francoise Beaufays, Rohit Prabhavalkar, Alexander H. Gruenstein, Kanishka Rao, Carolina Parada, Ian McGraw, David Rybach, Ouais Alsharif, Montse Gonzalez Arenas, Hasim Sak
Publikováno v:
ICASSP
We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-time on a Nexus 5 Android smartphone. We employ a quantized Long Short-T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dae983dd89cc96eaf0287640b8ced70d
https://doi.org/10.1109/icassp.2016.7472820
https://doi.org/10.1109/icassp.2016.7472820
Publikováno v:
INTERSPEECH
In this paper we describe the development of an accurate, smallfootprint, large vocabulary speech recognizer for mobile devices. To achieve the best recognition accuracy, state-of-the-art deep neural networks (DNNs) are adopted as acoustic models. A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::812bc58b7d21d84d32d2cb55557dfe5d
https://doi.org/10.21437/interspeech.2013-189
https://doi.org/10.21437/interspeech.2013-189