Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Xingyu Na"'
Publikováno v:
Chinese Journal of Electronics. 26:1239-1244
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::84bd389eb8ac6714a72ff62c77646434
https://doi.org/10.1049/cje.2017.07.004
https://doi.org/10.1049/cje.2017.07.004
Publikováno v:
O-COCOSDA
An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the largest corpus which is suitable for conducting the speech recognition research and building speech recognition systems for Mandarin. The recording procedure, includ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e381080d2067cdf16bedba63ad26386e
Autor:
Daniel Galvez, Daniel Povey, Sanjeev Khudanpur, Vijayaditya Peddinti, Xingyu Na, Yiming Wang, Pegah Ghahremani, Vimal Manohar
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c60e6d0acaffa8f2fffa905280784ee9
https://doi.org/10.21437/interspeech.2016-595
https://doi.org/10.21437/interspeech.2016-595
Publikováno v:
ICASSP
The connectionist temporal classification (CTC) loss function has several interesting properties relevant for automatic speech recognition (ASR): applied on top of deep recurrent neural networks (RNNs), CTC learns the alignments between speech frames
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8957febbf2b077adfe3ae9d37d31fdb
https://doi.org/10.1109/icassp.2016.7472152
https://doi.org/10.1109/icassp.2016.7472152
Publikováno v:
ICPR
Voice activity detection (VAD) is always important in many speech applications. In this paper, two VAD methods using novel features based on computational auditory scene analysis (CASA) are proposed. The first method is based on statistical model bas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2988a9bf0c435630bf5b207d4b7a3e15
https://doi.org/10.1109/icpr.2014.147
https://doi.org/10.1109/icpr.2014.147
Publikováno v:
ICME
Speech synthesizer is commonly used in human-computer interaction. In many applicational cases, the computing resource is limited while real-time synthesis is demanded. The HMM-based speech synthesis technique allows creating a natural voice quality
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c54c15a65b72baa08ebd9abb6044207c
https://doi.org/10.1109/icme.2014.6890197
https://doi.org/10.1109/icme.2014.6890197
Publikováno v:
ICASSP
HMM-based speech synthesis system (HTS) often generates buzzy and muffled speech. Such degradation of voice quality makes synthetic speech sound robotically rather than naturally. From this point, we suppose that synthetic speech is in a different sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e6ac8193eb41421d8a555da88ba9695
https://doi.org/10.1109/icassp.2014.6855141
https://doi.org/10.1109/icassp.2014.6855141
Publikováno v:
ISCSLP
This paper proposes a tone labeling technique for tonal language speech synthesis. Non-uniform segmentation using Viterbi alignment is introduced to determine the boundaries to get F0 symbols, which are used as tonal label to eliminate the mismatch b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e9803f868fe4d868039cbd8da92c07a8
https://doi.org/10.1109/iscslp.2012.6423467
https://doi.org/10.1109/iscslp.2012.6423467
Current very low bit rate speech coders are, due to complexity limitations, designed to work off-line. This paper investigates incremental speech coding that operates real-time and incrementally (i.e., encoded speech depends only on already-uttered s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::467100fc6f42a89e9aad96e7e609a965
https://infoscience.epfl.ch/record/206809
https://infoscience.epfl.ch/record/206809