Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Bronson Syiem"'
Comparison of Khasi speech representations with different spectral features and hidden Markov states
Publikováno v:
Journal of Electronic Science and Technology, Vol 19, Iss 2, Pp 100079- (2021)
In this paper, we present a comparison of the Khasi speech representations with four different spectral features and novel extension towards the development of Khasi speech corpora. These four features include linear predictive coding (LPC), linear p
Externí odkaz:
https://doaj.org/article/d2df9d577be346c6a1415bc960bcaf9d
Investigating Khasi Speech Recognition Systems using a Recurrent Neural Network-Based Language Model
Publikováno v:
International Journal of Engineering Trends and Technology. 70:269-274
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60891ef2ba760e21213d1618c5efeb69
https://doi.org/10.14445/22315381/ijett-v70i7p227
https://doi.org/10.14445/22315381/ijett-v70i7p227
Publikováno v:
Lecture Notes in Networks and Systems ISBN: 9789811901041
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c8fb3fabbcf0aedfa1cb1d0df1e452e
https://doi.org/10.1007/978-981-19-0105-8_53
https://doi.org/10.1007/978-981-19-0105-8_53
Autor:
L. Joyprakash Singh, Bronson Syiem
Publikováno v:
International Journal of Speech Technology. 24:419-424
Building a conventional automatic speech recognition (ASR) system based on hidden Markov model (HMM)/deep neural network (DNN) makes the system complex as it requires various modules such as acoustic, lexicon, linguistic resources, language models et
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::429103d98fd8f1e96a1f5178fc8d4f44
https://doi.org/10.1007/s10772-021-09811-5
https://doi.org/10.1007/s10772-021-09811-5
Publikováno v:
SSRN Electronic Journal.
In this work, various feature extraction techniques are implemented for a speech data corpus in Khasi Language. This paper provides a comparative performance analysis of widely used spectral features like Mel-Frequency Cepstrum Coefficients (MFCC), P
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f4c3a4c900ee08754dd7a54200cc986
https://doi.org/10.2139/ssrn.3515823
https://doi.org/10.2139/ssrn.3515823
Comparison of Khasi speech representations with different spectral features and hidden Markov states
Publikováno v:
Journal of Electronic Science and Technology. 19:100079
In this paper, we present a comparison of Khasi speech representations with four different spectral features and novel extension towards the development of Khasi speech corpora. These four features include linear predictive coding (LPC), linear predi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9227cb84923b3e0bfde8f7300bfab475
https://doi.org/10.1016/j.jnlest.2020.100079
https://doi.org/10.1016/j.jnlest.2020.100079
Publikováno v:
Advances in Communication, Devices and Networking ISBN: 9789811079009
A few researches have been conducted in the past decades for analyzing speech signal. For efficient study on the nature of the actual production of speech, the effect of vocal tract response and excitation source should be taken separately. However,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6864763c1ca1dcec5ffcc8b5cf57df1
https://doi.org/10.1007/978-981-10-7901-6_50
https://doi.org/10.1007/978-981-10-7901-6_50
Publikováno v:
Proceedings of the International Conference on Computing and Communication Systems ISBN: 9789811068898
Some speech parameters such as short-time energy, zero crossing rate, and minimum amplitude of the signal can be estimated directly by temporal analysis. This analysis is the easiest method of representing a speech signal since temporal features are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e210b0a08bfcdb00f9a413224e6c58a4
https://doi.org/10.1007/978-981-10-6890-4_36
https://doi.org/10.1007/978-981-10-6890-4_36
Autor:
L. Joyprakash Singh, Bronson Syiem
Publikováno v:
International Journal of Applied Pattern Recognition. 6:43
In this paper, deep neural network (DNN) is used to classify phonemes of the standard Khasi dialect which is one of the commonly used dialects in the state of Meghalaya. For this, clean speech data were recorded in the laboratory from native speakers
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39133365cf4ffee8818895ae6cb24a72
https://doi.org/10.1504/ijapr.2019.10026047
https://doi.org/10.1504/ijapr.2019.10026047