Multilingual Speech Analysis Essay

963 Words4 Pages

Multilingual Speech Analysis using Capstrum Coefficient features for text-dependent Speaker Identification System

Vinay Kumar Jain1, Dr.(Mrs.) Neeta Tripathi2
1Research Scholar SSTC(SSGI), Bhilai, India vinayrich_17@yahoo.co.in 2Principal, SSTC (SSEC), Bhilai, India neeta31dec@rediffmail.com Abstract— The demand for multilingual speaker identification system increases for countries like India where many people are able to speak more than one language. The Capstrum coefficient features analysis is important for observe the overall performance of the multilingual speaker identification system. The objective of the research work is to use Mel-Frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC) as feature components for the identification of a multilingual speaker. A model is proposed to identify the speaker by multi language speech signal of a speaker using MFCC ,delta-MFCCs and GFCC as acoustic features. For training and testing, neural network is used using resilient back propagation algorithm and radial basis functions and results are compared. The speech samples are recorded in three different languages Hindi, Marathi and Rajasthani. The extracted features of the speech signals of multiple languages are observed. In this experiment accuracy …show more content…

In India there are many peoples who are able to speak more than one language. Therefore there is a need to identify the effect of languages on a multilingual speaker identification system. When the Multilingual speaker identification system is being transferred to real applications, the need for greater adaptation in identification is required[13]. The performance of the monolingual speaker identification systems tends to decreases when speaker is speaking in another language. Therefore there is a need to make such systems which can work for multiple

More about Multilingual Speech Analysis Essay

Open Document