Predicting Automatic Speech Recognition Performance Over Communication Channels from Instrumental Speech Quality and Intelligibility Scores

2017 ◽  
Author(s):  
Laura Fernández Gallardo ◽  
Sebastian Möller ◽  
John Beerends
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Recognition Performance ◽  
Communication Channels ◽  
Speech Quality

Speech Feature Evaluation for Bangla Automatic Speech Recognition

2013 ◽  
pp. 169-208 ◽  
Author(s):  
Mohammed Rokibul Alam Kotwal ◽  
Foyzul Hassan ◽  
Mohammad Nurul Huda
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Recognition Performance ◽  
Dynamic Parameters ◽  
Mel Frequency Cepstral Coefficients ◽  
Phoneme Recognition ◽  
Hybrid Features ◽  
Feature Evaluation ◽  
Speech Feature ◽  
Speech Features

This chapter presents Bangla (widely known as Bengali) Automatic Speech Recognition (ASR) techniques by evaluating the different speech features, such as Mel Frequency Cepstral Coefficients (MFCCs), Local Features (LFs), phoneme probabilities extracted by time delay artificial neural networks of different architectures. Moreover, canonicalization of speech features is also performed for Gender-Independent (GI) ASR. In the canonicalization process, the authors have designed three classifiers by male, female, and GI speakers, and extracted the output probabilities from these classifiers for measuring the maximum. The maximization of output probabilities for each speech file provides higher correctness and accuracies for GI speech recognition. Besides, dynamic parameters (velocity and acceleration coefficients) are also used in the experiments for obtaining higher accuracy in phoneme recognition. From the experiments, it is also shown that dynamic parameters with hybrid features also increase the phoneme recognition performance in a certain extent. These parameters not only increase the accuracy of the ASR system, but also reduce the computation complexity of Hidden Markov Model (HMM)-based classifiers with fewer mixture components.

Sign in / Sign up

Export Citation Format

Share Document