Idioma:

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

Hassan, Foyzul ; Alam Kotwal, Mohammed Rokibul ; Rahman, Md. Mostafizur ; Nasiruddin, Mohammad ; Latif, Md. Abdul ; Nurul Huda, Mohammad

Advances in Computing and Communications, p.154-161 [Periódico revisado por pares]

Texto completo disponível

Citações Citado por

Título:
Local Feature or Mel Frequency Cepstral Coefficients - Which One Is Better for MLN-Based Bangla Speech Recognition?
Autor: Hassan, Foyzul ; Alam Kotwal, Mohammed Rokibul ; Rahman, Md. Mostafizur ; Nasiruddin, Mohammad ; Latif, Md. Abdul ; Nurul Huda, Mohammad
Assuntos: Automatic Speech Recognition ; Hidden Markov Model ; Local Feature ; Mel Frequency Cepstral Coefficient ; Multilayer Neural Network
É parte de: Advances in Computing and Communications, p.154-161
Descrição: 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 LFbased 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.
Títulos relacionados: Communications in Computer and Information Science
Editor: Berlin, Heidelberg: Springer Berlin Heidelberg
Idioma: Inglês

Voltar para lista de resultados