A Method of Automatic Speaker Recognition Using Cepstral Features and Vectorial Quantization

Automatic Speaker Recognition techniques are increasing the use of the speaker’s voice to control access to personalized telephonic services. This paper describes the use of vector quantization as a feature matching method, in an automatic speaker recognition system, evaluated with speech samples fr...

Full description

Saved in:
Bibliographic Details
Published inLecture notes in computer science pp. 146 - 153
Main Author de Lara, José Ramón Calvo
Format Book Chapter Conference Proceeding
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2005
Springer
SeriesLecture Notes in Computer Science
Subjects
Acoustic Vector
Applied sciences
Artificial intelligence
Cepstral Feature
Computer science; control theory; systems
Exact sciences and technology
Pattern recognition. Digital image processing. Computational geometry
Speaker Identification
Speaker Recognition
Speaker Verification
Speech and sound recognition and synthesis. Linguistics
Access control
Vector quantization
Image processing
Distributed database
Telephone network
Customization
Text
Pattern recognition
Speaker recognition
Signal quantization
Cepstrum
Speech recognition
Automatic recognition
Computer security
Voice
Speaker
Online AccessGet full text

Cover

More Information
Summary:Automatic Speaker Recognition techniques are increasing the use of the speaker’s voice to control access to personalized telephonic services. This paper describes the use of vector quantization as a feature matching method, in an automatic speaker recognition system, evaluated with speech samples from a SALA Spanish Venezuelan database for fixed telephone network. Results obtained reflect a good performance of the method in a text independent job in the context of sequences of digits.
ISBN:9783540298502
3540298509
ISSN:0302-9743
1611-3349
DOI:10.1007/11578079_16