Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Deepti Bhatia"'
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::637f1415711a50aa9b32c507220fa2b8
https://doi.org/10.2139/ssrn.4216345
https://doi.org/10.2139/ssrn.4216345
Autor:
Yanzhang He, Ke Hu, Rohit Prabhavalkar, Deepti Bhatia, Yu Zhang, Wei Li, David Qiu, Qiujia Li, Tara N. Sainath, Bo Li, Ian McGraw, Liangliang Cao
Publikováno v:
ICASSP
We study the problem of word-level confidence estimation in subword-based end-to-end (E2E) models for automatic speech recognition (ASR). Although prior works have proposed training auxiliary confidence models for ASR systems, they do not extend natu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::57fe29489a86717bd8521922ad80c736
https://doi.org/10.1109/icassp39728.2021.9413966
https://doi.org/10.1109/icassp39728.2021.9413966
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::caa6fd7775a79c4b59f01d3c3769a4a7
https://doi.org/10.21437/interspeech.2019-1209
https://doi.org/10.21437/interspeech.2019-1209
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
Publikováno v:
2015 International Conference on Industrial Instrumentation and Control (ICIC).
We are now living in the age of Big Data. The amount of data being generated every single second is beyond comprehensible. Human capacity for manual data analysis is nowhere near the rate at which new data is being captured. Video data is one of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd31af79305c9385f30b0c0f2665f860
https://doi.org/10.1109/iic.2015.7150802
https://doi.org/10.1109/iic.2015.7150802
Publikováno v:
2015 International Conference on Computing Communication Control and Automation.
With the growth in data collection through the use of media, it is necessary to classify this data in its resident format and with a good classification accuracy. Today the majority of the volume of data being gathered or shared is in the form of vid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b9b797844d6a2754b31fd1853072c770
https://doi.org/10.1109/iccubea.2015.138
https://doi.org/10.1109/iccubea.2015.138
Publikováno v:
2015 International Conference on Nascent Technologies in the Engineering Field (ICNTE).
Classification of Videos based on their content is becoming more and more essential everyday because of the vast amount of video data becoming available. Various Feature Extraction and data mining techniques can be used to perform Video Classificatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e0b1aac014a57a7a4acfcce41bb13cb0
https://doi.org/10.1109/icnte.2015.7029907
https://doi.org/10.1109/icnte.2015.7029907
Publikováno v:
2015 International Conference on Nascent Technologies in the Engineering Field (ICNTE).
Multimedia sharing has become a recent trend over the Internet among which videos are an integral part. In order to handle such large amount of video data, classification techniques are necessary. This paper provides a video classification technique
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::779d449d6a8d1483619d888d0cb1c22b
https://doi.org/10.1109/icnte.2015.7029942
https://doi.org/10.1109/icnte.2015.7029942
Publikováno v:
2015 International Conference on Communication, Information & Computing Technology (ICCICT).
Content based classification approach is becoming necessary to support the retrieval and indexing of images. This paper uses Color features of an image to form a feature vector on which data pre-processing is applied. These features are then used by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fbcc244b5ea5faf1623f6457fda35a3c
https://doi.org/10.1109/iccict.2015.7045737
https://doi.org/10.1109/iccict.2015.7045737
Publikováno v:
2015 International Conference on Communication, Information & Computing Technology (ICCICT).
Content Based Video Classification is becoming necessary for various video analysis applications to be able to handle humongous amounts of video data being generated & shared all over the Internet. This paper proposes use of DTTBTC for color based fe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b960032586fc97f6af46e54f8a05fb2d
https://doi.org/10.1109/iccict.2015.7045741
https://doi.org/10.1109/iccict.2015.7045741