Paper Info
Title
A novel approach in feature level for robust text-independent speaker identification system
Abstract
Over the decade, mel-frequency cepstral coefficient (MFCC) has been the most popular feature extraction method in the field of automatic speaker recognition. But in case of robust speaker recognition system, its performance is good for white noise contamination but not as good for other noises. We introduce speech-signal-based frequency cepstral coefficients (SFCC) in speaker recognition domain. In this method, frequency warping function is derived directly from the speech signal itself by considering equal area portions of the logarithm of the ensemble average short-time power spectrum of entire speech corpus. Speech-signal-based frequency warping function is very much similar to the frequency scale obtained through psycho-acoustic experiments known as mel scale and bark scale. We have proposed to use combination of filter banks of both the MFCC and SFCC in text-independent speaker identification. Speaker identification experiments are performed on POLY-COST database. The proposed technique gives better performance than the single streamed MFCC or SFCC based features for robust speaker identification system.
Year
DOI
Venue
2012
10.1109/IHCI.2012.6481824
Intelligent Human Computer Interaction
Keywords
Field
DocType
cepstral analysis,channel bank filters,feature extraction,speaker recognition,speech processing,white noise,POLY-COST database,SFCC based features,automatic speaker recognition,bark scale,ensemble average short-time power spectrum,feature extraction method,filter banks,frequency scale,mel scale,mel-frequency cepstral coefficient,psycho-acoustic experiments,robust speaker identification system,robust speaker recognition system,robust text-independent speaker identification system,single streamed MFCC,speaker recognition domain,speech corpus,speech signal,speech-signal-based frequency cepstral coefficients,speech-signal-based frequency warping function,white noise contamination,Robust speaker recognition,bark scale,feature extraction,mel scale,speech-signal-based frequency cepstral coefficient(SFCC),speech-signal-based frequency warping
Mel-frequency cepstrum,Speech processing,Pattern recognition,Computer science,Cepstrum,Bark scale,Speech recognition,Mel scale,Feature extraction,Speaker recognition,Speaker diarisation,Artificial intelligence
Conference
ISBN
Citations 
PageRank 
978-1-4673-4367-1
4
0.43
References 
Authors
7
2
Name
Order
Citations
PageRank
Susanta Kumar Sarangi140.43
Goutam Saha225523.17