Výsledky vyhledávání - "Mohammad Azharuddin Laskar"

Akademický článek

Deep neural network based two-stage Indian language identification system using glottal closure instants as anchor points

Autor: Chuya China Bhanja, Mohammad Azharuddin Laskar, Rabul Hussain Laskar, Sivaji Bandyopadhyay

Publikováno v: Journal of King Saud University: Computer and Information Sciences, Vol 34, Iss 4, Pp 1439-1454 (2022)

This paper presents a two-stage Indian language identification (TS-LID) system which is made up of a tonal/non-tonal pre-classification and individual language identification modules. It studies the effectiveness of Mean Hilbert envelope coefficients

Externí odkaz: https://doaj.org/article/5ab519ec2b1f45f8ac5ecb3b65c62876

Zobrazit plný text záznamu

Raw Waveform Based Speaker Identification Using Deep Neural Networks

Autor: Banala Saritha, Mohammad Azharuddin Laskar, Rabul Hussain Laskar, Madhuchhanda Choudhury

Publikováno v: 2022 IEEE Silchar Subsection Conference (SILCON).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::18b92396d696c65a0a7583890654fbb8
https://doi.org/10.1109/silcon55242.2022.10028890

Zobrazit plný text záznamu

A Comprehensive Review on Speaker Recognition

Autor: Banala Saritha, Mohammad Azharuddin Laskar, Rabul Hussain Laskar

Publikováno v: Advances in Speech and Music Technology ISBN: 9783031184437

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7a9a82871cf1f8d9a4a219f8c7f612ec
https://doi.org/10.1007/978-3-031-18444-4_1

Zobrazit plný text záznamu

Speaker-Phrase-Specific Adaptation of PLDA Model for Improved Performance in Text-Dependent Speaker Verification

Autor: Rabul Hussain Laskar, Mohammad Azharuddin Laskar, Chuya China Bhanja

Publikováno v: Circuits, Systems, and Signal Processing. 40:5127-5151

The i-vector/probabilistic linear discriminant analysis (PLDA) framework has been popularly used in the field of speaker verification for a long time. Lately, the introduction of online i-vectors and its integration with dynamic time warping template

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::20bf535d7aa1d5b40db84129d16b070f
https://doi.org/10.1007/s00034-021-01713-w

Zobrazit plný text záznamu

Modelling multi-level prosody and spectral features using deep neural network for an automatic tonal and non-tonal pre-classification-based Indian language identification system

Autor: Chuya China Bhanja, Rabul Hussain Laskar, Mohammad Azharuddin Laskar

Publikováno v: Language Resources and Evaluation. 55:689-730

In this paper an attempt has been made to prepare an automatic tonal and non-tonal pre-classification-based Indian language identification (LID) system using multi-level prosody and spectral features. Languages are first categorized into tonal and no

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::50ae649461c9072ed1f797a48db2ccc5
https://doi.org/10.1007/s10579-020-09527-z

Zobrazit plný text záznamu

HiLAM-state discriminative multi-task deep neural network in dynamic time warping framework for text-dependent speaker verification

Autor: Mohammad Azharuddin Laskar, Rabul Hussain Laskar

Publikováno v: Speech Communication. 121:29-43

This paper builds on a multi-task Deep Neural Network (DNN), which provides an utterance-level feature representation called j-vector, to implement a Text-dependent Speaker Verification (TDSV) system. This technique exploits the speaker idiosyncrasie

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::378a7b41c46ae9198e99f58e32e7c9c9
https://doi.org/10.1016/j.specom.2020.03.007

Zobrazit plný text záznamu

Filterbank Optimization for Text-Dependent Speaker Verification by Evolutionary Algorithm Using Spline-Defined Design Parameters

Autor: Rabul Hussain Laskar, Mohammad Azharuddin Laskar

Publikováno v: Arabian Journal for Science and Engineering. 44:9703-9718

Mel frequency cepstral coefficients (MFCCs) have been the most predominantly used spectral features in many a speech-based application. It was primarily introduced to address speech recognition and was later adopted for various other applications suc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::517f9303b9dd6bb2bfc47122179055db
https://doi.org/10.1007/s13369-019-04090-4

Zobrazit plný text záznamu

Integrating DNN–HMM Technique with Hierarchical Multi-layer Acoustic Model for Text-Dependent Speaker Verification

Autor: Mohammad Azharuddin Laskar, Rabul Hussain Laskar

Publikováno v: Circuits, Systems, and Signal Processing. 38:3548-3572

Subspace techniques, such as i-vector/probabilistic linear discriminant analysis and joint factor analysis, have been the most commonly used techniques in the field of text-dependent speaker verification. These techniques, however, do not model the t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f53a62447c1c30bedecb33392f711d44
https://doi.org/10.1007/s00034-019-01103-3

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání