Local Feature or Mel Frequency Cepstral Coefficients - Which One Is Better for MLN-Based Bangla Speech Recognition?

被引：0

作者：

Hassan, Foyzul ^{[1
]}

Kotwal, Mohammed Rokibul Alam ^{[1
]}

Rahman, Md Mostafizur ^{[1
]}

Nasiruddin, Mohammad ^{[2
]}

Latif, Md Abdul ^{[2
]}

Huda, Mohammad Nurul ^{[1
]}

机构：

[1] United Int Univ, Dhaka, Bangladesh

[2] Univ Asia Pacific, Dhaka, Bangladesh

来源：

ADVANCES IN COMPUTING AND COMMUNICATIONS, PT 2 | 2011年 / 191卷

关键词：

Local Feature; Mel Frequency Cepstral Coefficient; Multilayer Neural Network; Hidden Markov Model; Automatic Speech Recognition;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper discusses the dominancy of local features (LFs), as input to the multilayer neural network (MLN), extracted from a Bangla input speech over mel frequency cepstral coefficients (MFCCs). Here, LF-based method comprises three stages: (i) LF extraction from input speech, (ii) phoneme probabilities extraction using MLN from LF and (iii) the hidden Markov model (HMM) based classifier to obtain more accurate phoneme strings. In the experiments on Bangla speech corpus prepared by us, it is observed that the LF-based automatic speech recognition (ASR) system provides higher phoneme correct rate than the MFCC-based system. Moreover, the proposed system requires fewer mixture components in the HMMs.

引用

页码：154 / +

页数：2

共 40 条

[1] Palmprint recognition based on Mel frequency Cepstral coefficients feature extraction
Fahmy, Maged M. M.
AIN SHAMS ENGINEERING JOURNAL, 2010, 1 (01) : 39 - 47
[2] Chip design of mel frequency cepstral coefficients for speech recognition
Wang, JC
Wang, JF
Weng, YS
2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 3658 - 3661
[3] Improved DTW Speech Recognition Algorithm Based on the MEL Frequency Cepstral Coefficients
Wei Ming-zhe
Li Xi
Ren Li-mian
12TH ANNUAL MEETING OF CHINA ASSOCIATION FOR SCIENCE AND TECHNOLOGY ON INFORMATION AND COMMUNICATION TECHNOLOGY AND SMART GRID, 2010, : 235 - 238
[4] Combining Mel Frequency Cepstral Coefficients and Fractal Dimensions for Automatic Speech Recognition
Ezeiza, Aitzol
Lopez de Ipina, Karmele
Hernandez, Carmen
Barroso, Nora
ADVANCES IN NONLINEAR SPEECH PROCESSING, 2011, 7015 : 183 - +
[5] One Solution of Extension of Mel-Frequency Cepstral Coefficients Feature Vector for Automatic Speaker Recognition
Jokic, Ivan D.
Jokic, Stevan D.
Delic, Vlado D.
Peric, Zoran H.
INFORMATION TECHNOLOGY AND CONTROL, 2020, 49 (02): : 224 - 236
[6] Mel Frequency Cepstral Coefficients Based Similar Albanian Phonemes Recognition
Karahoda, Bertan
Pireva, Krenare
Imran, Ali Shariq
HUMAN INTERFACE AND THE MANAGEMENT OF INFORMATION: INFORMATION, DESIGN AND INTERACTION, PT I, 2016, 9734 : 491 - 500
[7] Recognition of Human Speech Emotion Using Variants of Mel-Frequency Cepstral Coefficients
Palo, Hemanta Kumar
Chandra, Mahesh
Mohanty, Mihir Narayan
ADVANCES IN SYSTEMS, CONTROL AND AUTOMATION, 2018, 442 : 491 - 498
[8] A New Approach for Fingerprint Recognition Based on Mel Frequency Cepstral Coefficients
Hashad, F. G.
Halim, T. M.
Diab, S. M.
Sallam, B. M.
2009 INTERNATIONAL CONFERENCE ON COMPUTER ENGINEERING AND SYSTEMS (ICCES 2009), 2009, : 263 - +
[9] Emotion Recognition from Speech Signal Using Mel-Frequency Cepstral Coefficients
Korkmaz, Onur Erdem
Atasoy, Ayten
2015 9TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONICS ENGINEERING (ELECO), 2015, : 1254 - 1257
[10] Robust Acoustic Speech Feature Prediction From Noisy Mel-Frequency Cepstral Coefficients
Milner, Ben
Darch, Jonathan
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (02): : 338 - 347

← 1 2 3 4 →