Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Shafkat Kibria"'
Autor:
Ahnaf Mozib Samin, M. Humayon Kobir, Md. Mushtaq Shahriyar Rafee, M. Firoz Ahmed, Mehedi Hasan, Partha Ghosh, Shafkat Kibria, M. Shahidur Rahman
Publikováno v:
IEEE Access, Vol 12, Pp 34527-34538 (2024)
Despite huge improvements in automatic speech recognition (ASR) employing neural networks, ASR systems still suffer from a lack of robustness and generalizability issues due to domain shifting. This is mainly because principal corpus design criteria
Externí odkaz:
https://doaj.org/article/eb4177ff73a746a3be67a7a5aef4e133
Publikováno v:
IEEE Access, Vol 8, Pp 35200-35221 (2020)
Accented pronunciation variability is one of the key elements that deteriorate the accuracy of the automatic speech recognition (ASR). This article reports the results of the acoustic analysis of the two groups of speakers' variability caused by regi
Externí odkaz:
https://doaj.org/article/506a8e037f7548d3b9ea2038391d2f94
Autor:
Shafkat Kibria, Ahnaf Mozib Samin, M. Humayon Kobir, M. Shahidur Rahman, M. Reza Selim, M. Zafar Iqbal
Publikováno v:
Speech Communication. 136:84-97
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b88fa52455054bce64a2ef2c327da4de
https://doi.org/10.1016/j.specom.2021.12.004
https://doi.org/10.1016/j.specom.2021.12.004
Publikováno v:
Acoustical Science and Technology. 42:252-260
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4caf659a408e4b2e24d36fe4af60ed34
https://doi.org/10.1250/ast.42.252
https://doi.org/10.1250/ast.42.252
Publikováno v:
IEEE Access. 8:35200-35221
Accented pronunciation variability is one of the key elements that deteriorate the accuracy of the automatic speech recognition (ASR). This article reports the results of the acoustic analysis of the two groups of speakers’ variability caused by re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::35e79d0ab8d8daf4f06e2e913ace28c9
https://doi.org/10.1109/access.2020.2974799
https://doi.org/10.1109/access.2020.2974799
Publikováno v:
2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f1d2e6c483f38b509bb5ae3a843a976
https://doi.org/10.1109/ccwc54503.2022.9720862
https://doi.org/10.1109/ccwc54503.2022.9720862
Publikováno v:
Proceedings of International Joint Conference on Computational Intelligence ISBN: 9789811536069
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd918cd401c8bef59f95a1fd76e3c6e1
https://doi.org/10.1007/978-981-15-3607-6_3
https://doi.org/10.1007/978-981-15-3607-6_3
Publikováno v:
2019 International Conference on Bangla Speech and Language Processing (ICBSLP).
This article presents a lexicon-free Automatic Speech Recognition (ASR) system for the Bangla language and investigates an open-source large Bangla ASR corpus, which proved by OpenSLR. The model has been trained using improved MFCC acoustic features
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d54e3d18d10d3cfea17c0f816a338c9
https://doi.org/10.1109/icbslp47725.2019.201544
https://doi.org/10.1109/icbslp47725.2019.201544
Publikováno v:
2019 International Conference on Electrical, Computer and Communication Engineering (ECCE).
Nowadays, deep learning is the most reliable approaches in the field of speech recognition to do the Acoustic modeling. Working with a language like “Bengali” that is not very resource-rich in terms of availability of parallel data (i.e. speech w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20dcfabfe8dfa535bebaa527249d3f2e
https://doi.org/10.1109/ecace.2019.8679341
https://doi.org/10.1109/ecace.2019.8679341
Publikováno v:
2018 International Conference on Bangla Speech and Language Processing (ICBSLP).
In this work, different Gaussian Mixture Model-Hidden Markov Model(GMM-HMM) based and Deep Neural Network (DNN-HMM) based models have been analyzed for speech recognition in Bangla language to build a voice search module for search engine pipilika 1.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4494e593a5b60cbe3da9b8d2e8c73a79
https://doi.org/10.1109/icbslp.2018.8554944
https://doi.org/10.1109/icbslp.2018.8554944