<<A>> two-level speaker identification system based on vector quantization

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F01%3A00064791" target="_blank" >RIV/49777513:23520/01:00064791 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
<<A>> two-level speaker identification system based on vector quantization
Original language description
This paper presents an approach to text independent speaker identification based on vector quantization. In our experiments we tested a new structure of the codebook, in which information about all reference speakers is integrated. Due to the propertiesof the identification system based on such a structure we decided to design a two-level identification system. The first stage of this system is formed by a common codebook whereas the second stage consists of standard codebooks corresponding to reference speakers. In our tests we used two types of features: LPC cepstral coefficients (LPCCs) and mel-frequency cepstral coefficients (MFCCs). The experiments were performed in a closed group of 300 speakers.
Czech name
—
Czech description
—

Project
<a href="/en/project/GV102%2F96%2FK087" target="_blank" >GV102/96/K087: Theory and application of speach communication in czech</a><br>
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
2001
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
<<A>> two-level speaker identification system based on vector quantization
ISBN
—
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
Université Paul Sabatier
Place of publication
Toulouse
Event location
Toulouse
Event date
Jan 1, 2001
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)