Zobrazeno 1 - 10
of 220
pro vyhledávání: '"Longbiao Wang"'
Autor:
Khomdet Phapatanaburi, Longbiao Wang, Meng Liu, Seiichi Nakagawa, Talit Jumphoo, Peerapong Uthansakul
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-14 (2024)
Abstract Shouted and normal speech classification plays an important role in many speech-related applications. The existing works are often based on magnitude-based features and ignore phase-based features, which are directly related to magnitude inf
Externí odkaz:
https://doaj.org/article/00f296c9c67e48219caa4a7c2ced5455
Publikováno v:
Electronics Letters, Vol 59, Iss 11, Pp n/a-n/a (2023)
Abstract In real life, either the subjective factors of speakers or the objective environment degrades the performance of automatic speech recognition (ASR). This study focuses on one of the subjective factors, accented speech, and attempts to build
Externí odkaz:
https://doaj.org/article/406cc51820de41c59f15d077bcf2c604
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2022, Iss 1, Pp 1-10 (2022)
Abstract Conventional automatic speech recognition (ASR) and emerging end-to-end (E2E) speech recognition have achieved promising results after being provided with sufficient resources. However, for low-resource language, the current ASR is still cha
Externí odkaz:
https://doaj.org/article/6dd8a3750e2547d9b60e5746b3f116d5
Autor:
Zeyan Oo, Longbiao Wang, Khomdet Phapatanaburi, Meng Liu, Seiichi Nakagawa, Masahiro Iwahashi, Jianwu Dang
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2019, Iss 1, Pp 1-11 (2019)
Abstract There are many studies on detecting human speech from artificially generated speech and automatic speaker verification (ASV) that aim to detect and identify whether the given speech belongs to a given speaker. Recent studies demonstrate the
Externí odkaz:
https://doaj.org/article/dd522b65ad3d40f1a43e1561162f4a09
Publikováno v:
IEEE Access, Vol 7, Pp 75798-75809 (2019)
Previous studies of speech emotion recognition using either empirical features (e.g., F0, energy, and voice probability) or spectrogram-based statistical features. The empirical features can highlight the human knowledge of emotion recognition, while
Externí odkaz:
https://doaj.org/article/b5b74ad333e849c98bc3ff3659bd33c8
Publikováno v:
IEEE Access, Vol 7, Pp 183614-183625 (2019)
Recent studies have reported the success of linear prediction analysis (LPA)-related features, which are extracted as a short-term spectral feature for replay attack detection due to the advantage of the imperfection in the LPA-based signal produced
Externí odkaz:
https://doaj.org/article/eb2b618ec4fa4e1ea712b46ab893e4db
Autor:
Khomdet Phapatanaburi, Wongsathon Pathonsuwan, Longbiao Wang, Patikorn Anchuen, Talit Jumphoo, Prawit Buayai, Monthippa Uthansakul, Peerapong Uthansakul
Publikováno v:
Symmetry, Vol 14, Iss 4, p 777 (2022)
Recent studies have reported that the performance of Automatic Speech Recognition (ASR) technologies designed for normal speech notably deteriorates when it is evaluated by whispered speech. Therefore, the detection of whispered speech is useful in o
Externí odkaz:
https://doaj.org/article/4853e7bff629492aaa810ad2df9b3f2e
Publikováno v:
Discrete Dynamics in Nature and Society, Vol 2020 (2020)
Mapping and masking are two important speech enhancement methods based on deep learning that aim to recover the original clean speech from corrupted speech. In practice, too large recovery errors severely restrict the improvement in speech quality. I
Externí odkaz:
https://doaj.org/article/8cdbc9a5ce1f4af3a1440815e947399a
Publikováno v:
IEEE Signal Processing Letters. 30:344-348
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 31:1024-1036