Czasopismo | ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA | Rocznik 2011 - zeszyt 5

Experimental speaker recognition investigations using head / torso simulator and telephone transmission

nr katalogowy: 59593

This paper presents a system and experimental results of text independent speaker recognition over telephone network. In general, a speaker recognition problem, as a technical problem, consists in assigning the speech signal to an appropriate model of the speakerfs signal. This problem can be decomposed into several phases, which should be developed. Acquisition of speech signal using microphone and analog-to-digital converter is a relatively simple task, which delivers very good digital representation of the real speech signal. Building a model of the signal in order to identify or verify persons, who are speaking, requires a lot of efforts. This field of research is well developed with certain solutions but one says that up to now only local maximum has been reached [1]. The state-of-the-art solutions allow for real applications but the present research is devoted to new applications, which are more demanding. Speech is a very efficient way of communication not only between human beings but also between humans and machines. Among the most important every day activities is are telephone calls and other steadily growing customer services. Telephone call is a very convenient way to access private or restricted data in banks, during e-learning etc. In such situations speaker recognition is required. Another example is speech recognition without speaker awareness, like in monitoring or surveillance systems. In order to evaluate a speaker recognition system various test speech signals have to be used. The signal may be a soft voice (not loud enough), negligent or interrupted. The difficulty is that the model has to be robust to any undesired speech signal variations. Speech is very often acquired in the presence of other background sounds like wind, other voices, and noise. Such signals are collected in speech databases (e.g., those available through the Linguistic Data Consortium) or can be generated using simulators. In[...]

Jeśli masz wykupiony/przyznany dostęp - zaloguj się. Skorzystaj z naszych propozycji zakupu!

Publikacja


e-Publikacja (format pdf) - nr 1148 "Metody wzorcowania przetw..." licencja: Osobista Produkt cyfrowy	10.00 zł

Zeszyt


ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA - e-zeszyt (pdf) 2011-5 licencja: Osobista Produkt cyfrowy	35.00 zł

Prenumerata

ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA - prenumerata cyfrowa
licencja: Osobista

Produkt cyfrowy
Nowość

420.00 zł

ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA - papierowa prenumerata roczna + wysyłka
licencja: Osobista

Szczegóły pakietu

Nazwa
ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA - papierowa prenumerata roczna	528.00 zł brutto 488.89 zł netto 39.11 zł VAT (stawka VAT 8%)
ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA - pakowanie i wysyłka	42.00 zł brutto 34.15 zł netto 7.85 zł VAT (stawka VAT 23%)

570.00 zł

ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA - PAKIET prenumerata PLUS
licencja: Osobista

Szczegóły pakietu

Nazwa
ELEKTRONIKA - KONSTRUKCJE, TECHNOLOGIE, ZASTOSOWANIA - PAKIET prenumerata PLUS (Prenumerata papierowa + dostęp do portalu sigma-not.pl + e-prenumerata)	636.00 zł brutto 588.89 zł netto 47.11 zł VAT (stawka VAT 8%)

636.00 zł

Zeszyt

2011-5

Twój Koszyk

Publikacja

Zeszyt

Prenumerata

Zeszyt

Czasopisma