An overview of speaker recognition

<p>Speaker recognition has been studied for many years and has been a hot topic. This paper presents an overview of speaker recognition methods, which include the classical and the state-of-art methods. According to the modular components of speaker recognition system, we fi rstly introducedth...

Ful tanımlama

Kaydedildi:
Detaylı Bibliyografya
Asıl Yazarlar: Junxia Liu (Yazar), CL Philip Chen (Yazar), Tieshan Li (Yazar), Yi Zuo (Yazar), Peichao He (Yazar)
Materyal Türü: Kitap
Baskı/Yayın Bilgisi: Trends in Computer Science and Information Technology - Peertechz Publications, 2019-08-28.
Konular:
Online Erişim:Connect to this object online.
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

MARC

LEADER 00000 am a22000003u 4500
001 peertech__10_17352_tcsit_000009
042 |a dc 
100 1 0 |a Junxia Liu  |e author 
700 1 0 |a  CL Philip Chen  |e author 
700 1 0 |a  Tieshan Li  |e author 
700 1 0 |a  Yi Zuo  |e author 
700 1 0 |a Peichao He  |e author 
245 0 0 |a An overview of speaker recognition 
260 |b Trends in Computer Science and Information Technology - Peertechz Publications,   |c 2019-08-28. 
520 |a <p>Speaker recognition has been studied for many years and has been a hot topic. This paper presents an overview of speaker recognition methods, which include the classical and the state-of-art methods. According to the modular components of speaker recognition system, we fi rstly introducedthe fundamentals of speaker recognition, which are mainly divided into two parts: feature extraction and speaker modeling. The most commonly speech features used in speaker recognition were elaborated fi rstly. In particular, the recent progress of deep neural network proposes a new approach of feature extraction and has become the technology trend. Secondly, the classical approaches of speaker recognition model were introduced, and elaborated the recent progress of deep learning speaker recognition. This paper especially provides an in-depth analysis on end-to-end model which consists of a training component to extract features, an enrollment component to training the speaker model, and an evaluation component with appropriate loss function for optimization. The fi nal part concludes the paper with discussion on future trends.</p> 
540 |a Copyright © Junxia Liu et al. 
546 |a en 
655 7 |a Review Article  |2 local 
856 4 1 |u https://doi.org/10.17352/tcsit.000009  |z Connect to this object online.