The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 53-609
Full Name: Isha Dhawan
Position: Student
Age: ON
Sex: Female
Address: C2 204, Lotus Pond, Vaibhav Khand, Indirapuram, Ghaziabad
Country: INDIA
Tel: 8872987068
Tel prefix:
Fax:
E-mail address: cheezesha@gmail.com
Other E-mails: ishadhwan@yahoo.co.in
Title of the Paper: Integration of text-dependent Speaker and Speech Recognition System
Authors as they appear in the Paper: Isha Dhawan, Dr. Neelu Jain
Email addresses of all the authors: cheezesha@gmail.com, neelujn@hotmail.com
Number of paper pages: 10
Abstract: Speech is the most important and primary mode of communication among human being and also the most natural and efficient form of exchanging information among humans. Various fields for research in speech processing are Speech Recognition, Speaker Recognition, Speech Synthesis, Speech Coding etc. This paper presents a detailed study of text-dependent Speaker and Speech Recognition system. Speaker recognition system uses vector quantization (VQ) as the modeling technique and the features of the speech signal are extracted using Mel Frequency Cepstum Coefficients (MFCC). K-means clustering algorithm has been used to obtain the vector quantized codebook. For speaker-independent Speech recognition system, the formant frequencies of the word sample are used to determine the unknown word. Speaker recognition system yields highest accuracy using Hanning window and Mel perceptual feature extraction realized with 35 filter bank. Accuracy also improves as the number of vector!
s in the VQ codebook is increased from 64 to 100 whereas for Speech recognition highest accuracy obtained is 95%.
Keywords: Formants, Feature extraction, K-Means clustering, Mel Frequency Cepsrtum Coefficients, Vector Quantization
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 110.234.205.162
