Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Ali Abavisani"'
Autor:
Piotr Żelasko, Siyuan Feng, Laureano Moro Velázquez, Ali Abavisani, Saurabhchand Bhati, Odette Scharenborg, Mark Hasegawa-Johnson, Najim Dehak
The high cost of data acquisition makes Automatic Speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a written script, or for which the phone inventories remain unknown. Past wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4da3ffbb4e52177d36662d6fc394f9c9
Autor:
Dalibor Petkovic, Mohammed Abdullahi Mu’azu, Javad Katebi, Karzan Wakil, Normaniza Osman, Majid Khorami, Ali Abavisani, Puteri Azura Sari, Naser Ghaffari, Meldi Suhatril, Esmaeil Sadeghi Chahnasir
Publikováno v:
Engineering with Computers. 36:1347-1354
This study predicts the investigation of surface eco-protection techniques for cohesive soil slopes along the selected Guthrie Corridor Expressway stretch by way of analyzing a new set of probabilistic models using a hybrid technique of artificial ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::35d13f85ba7bbad93cd137e98e3a547d
https://doi.org/10.1007/s00366-019-00768-3
https://doi.org/10.1007/s00366-019-00768-3
Autor:
Ali Abavisani, Mark Hasegawa-Johnson
Publikováno v:
INTERSPEECH
In this article, we provide a model to estimate a real-valued measure of the intelligibility of individual speech segments. We trained regression models based on Convolutional Neural Networks (CNN) for stop consonants \textipa{/p,t,k,b,d,g/} associat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00961db6a0bbb76ebacaddfd750fea36
https://doi.org/10.21437/interspeech.2020-2121
https://doi.org/10.21437/interspeech.2020-2121
Autor:
Najim Dehak, Odette Scharenborg, Mark Hasegawa-Johnson, Siyuan Feng, Laureano Moro-Velázquez, Piotr Zelasko, Ali Abavisani
Publikováno v:
ICASSP
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
The idea of combining multiple languages' recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been shown to le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0cd0602e5019cae609e3f5b43f6e0970
Autor:
Jont B. Allen, Ali Abavisani
A speech-based hearing test is designed to identify the susceptible error-prone phones for individual hearing impaired (HI) ear. Only robust tokens in the experiment noise levels had been chosen for the test. The noise-robustness of tokens is measure
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4898aa3b41de2a2ac5a8ba7096953dab
Autor:
Ali Abavisani, Jont B. Allen
Publikováno v:
The Journal of the Acoustical Society of America. 143:1746-1746
A key factor on correct phone recognition in Normal Hearing (NH) and Hearing Impaired (HI) listeners, is the intensity of primary cue. One can assess this intensity for a given speech sound, by examining it at various Signal to Noise Ratios (SNR) pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a975d538fe8d869c6b6f0ba34224e7aa
https://doi.org/10.1121/1.5035700
https://doi.org/10.1121/1.5035700
Autor:
Jont B. Allen, Ali Abavisani
Publikováno v:
The Journal of the Acoustical Society of America. 141:3633-3633
The goal of this study is to quantify a given hearing aid insertion gain using a consonant recognition based measure, for ears having sensorineural hearing loss. The basic question addressed is how a treatment impacts phone recognition, relative to a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::832e99ae3528c54c4cc899f4b841aba3
https://doi.org/10.1121/1.4987822
https://doi.org/10.1121/1.4987822
Autor:
Jont B. Allen, Ali Abavisani
Publikováno v:
The Journal of the Acoustical Society of America. 139:2188-2188
The identification of very short phoneme segments of speech is the key to understanding speech in chopped noise. Over the last 12 years, UIUC has repeated Miller-Nicely's 1955 phone recognition experiment, with 60 subjects and six SNRs, from quiet to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de9501308f8330dc33e45ed51915faa8
https://doi.org/10.1121/1.4950512
https://doi.org/10.1121/1.4950512
Publikováno v:
CrownCom
In This paper, we propose a new method to recognizing and distinguishing among 8-PSK modulated signal and π/4-shifted QPSK, from the samples of received noisy and faded PSK signal. The proposed algorithm is based on computation of relative Euclidean
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e78dad1edd8f0d4ac4b3e501671bb25
https://doi.org/10.1109/crowncom.2009.5189385
https://doi.org/10.1109/crowncom.2009.5189385
Publikováno v:
Scopus-Elsevier
ICT4AWE
ICT4AWE
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ebf614a480dcc5bf0c9d6bff2f334f5
http://www.scopus.com/inward/record.url?eid=2-s2.0-85091441899&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85091441899&partnerID=MN8TOARS