8

Study|Survey of Speaker Recognition System in NN Method

 2 years ago
source link: https://zjcqn.github.io/posts/Speaker_recognition_system_survey/
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

Study|Survey of Speaker Recognition System in NN Method

Posted 1 year ago2021-01-23T15:33:00+08:00 by 陈钱牛

image-20210123191019268

Feature Extraction

MFCC, PLP, SDC, PNCC, GFCC, CQCC.

Bottleneck, Phoneme Posterior Probability.

LLD/OpenSmile, Speech attributes, Acoustic-to-articulatory inversion, subglottal.

IMFCC, Modified Group Delay.

Variability Compensation

Backend Classification

Joint Bayesian

Cosine Similarity

Network Structure

Feed-forward DNN(FF-DNN): D-vector

RNN/LSTM

TDNN: x-vector

This post is licensed under CC BY 4.0 by the author.
Share

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK