Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Mousmita Sarma"'
Segmentation and Classification of Vowel Phonemes of Assamese Speech Using a Hybrid Neural Framework
Autor:
Mousmita Sarma, Kandarpa Kumar Sarma
Publikováno v:
Applied Computational Intelligence and Soft Computing, Vol 2012 (2012)
In spoken word recognition, one of the crucial points is to identify the vowel phonemes. This paper describes an Artificial Neural Network (ANN) based algorithm developed for the segmentation and recognition of the vowel phonemes of Assamese language
Externí odkaz:
https://doaj.org/article/8dbb515e5ce54aa9a0382de4bdde6688
Publikováno v:
International Journal of Speech Technology. 23:223-240
We propose a method which provides age of the speaker as an additional information while training a machine learning model for gender identification. To achieve this objective, we design a multi-task learning Deep Neural Network (DNN) model where the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7dd0f79ec24ce65462f2f3b550f5c715
https://doi.org/10.1007/s10772-020-09680-4
https://doi.org/10.1007/s10772-020-09680-4
Autor:
Kandarpa Kumar Sarma, Mousmita Sarma
Publikováno v:
IEEE Intelligent Systems. 33:40-52
Dialects of languages demonstrate dependency on both speaker and sound-unit (phone)-related information, which encompasses the problem of dialect identification (DID) under the domain of language identification (LID). The DID task is more complicated
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dcd4b226a0e3171fc004b89a59242536
https://doi.org/10.1109/mis.2018.111144010
https://doi.org/10.1109/mis.2018.111144010
Publikováno v:
Lecture Notes in Networks and Systems ISBN: 9789811527739
We propose raw speech waveform-based end-to-end deep neural network (DNN) architectures to estimate age and gender of children within the age range of 4–14 years. To achieve this objective, we design single-task and multi-task learning DNN configur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0f5f938723436c208b0559ab9e52674e
https://doi.org/10.1007/978-981-15-2774-6_1
https://doi.org/10.1007/978-981-15-2774-6_1
Autor:
Najim Dehak, Nagendra Kumar Goel, Mousmita Sarma, Pegah Ghahremani, Daniel Povey, Kandarpa Kumar Sarma
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8ebfd8de5f6239d50196c5783abe8b6
https://doi.org/10.21437/interspeech.2019-2093
https://doi.org/10.21437/interspeech.2019-2093
Autor:
Daniel Povey, Mousmita Sarma, Nagendra Kumar Goel, Najim Dehak, Pegah Ghahremani, Kandarpa Kumar Sarma
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87dc2f7a6979e6a2d88b12c76eb8eab3
https://doi.org/10.21437/interspeech.2018-1353
https://doi.org/10.21437/interspeech.2018-1353
Publikováno v:
Journal of Artificial Intelligence and Soft Computing Research. 5:59-70
In this work, a class of neuro-computational classifiers are used for classification of fricative phonemes of Assamese language. Initially, a Recurrent Neural Network (RNN) based classifier is used for classification. Later, another neuro fuzzy class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da87bb341431b9e8df8ab4dcb21b0985
https://doi.org/10.1515/jaiscr-2015-0019
https://doi.org/10.1515/jaiscr-2015-0019
Autor:
Kandarpa Kumar Sarma, Mousmita Sarma
Publikováno v:
International Journal of Parallel, Emergent and Distributed Systems. 28:370-382
Phonemes are the smallest distinguishable unit of speech signal. Segmentation of a phoneme from its word counterpart is a fundamental and crucial part in speech processing because an initial phoneme is used to activate words starting with that phonem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a1f027bbc1e308b377e53ab516a3b5c
https://doi.org/10.1080/17445760.2013.791824
https://doi.org/10.1080/17445760.2013.791824
Autor:
Kandarpa Kumar Sarma, Mousmita Sarma
Publikováno v:
Journal of Intelligent Systems, Vol 22, Iss 2, Pp 111-130 (2013)
Vowel phonemes are a part of any acoustic speech signal. Vowel sounds occur in speech more frequently and with higher energy. Therefore, vowel phoneme can be used to extract different amounts of speaker discriminative information in situations where
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9ddb9db293735685f4e6973fbaae568
https://doi.org/10.1515/jisys-2012-0050
https://doi.org/10.1515/jisys-2012-0050
Autor:
Kandarpa Kumar Sarma, Mousmita Sarma
Publikováno v:
Applied Soft Computing. 13:2281-2291
Initial phoneme is used in spoken word recognition models. These are used to activate words starting with that phoneme in spoken word recognition models. Such investigations are critical for classification of initial phoneme into a phonetic group. A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cfc883b99f1876ce6ac406c5ebbf974d
https://doi.org/10.1016/j.asoc.2013.01.004
https://doi.org/10.1016/j.asoc.2013.01.004