Deep factorization for speech signal

02/27/2018
by   Lantian Li, et al.
Tsinghua University
0

Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors. An intuitive idea is to factorize each speech frame into individual informative factors, though it turns out to be highly difficult. Recently, we found that speaker traits, which were assumed to be long-term distributional properties, are actually short-time patterns, and can be learned by a carefully designed deep neural network (DNN). This discovery motivated a cascade deep factorization (CDF) framework that will be presented in this paper. The proposed framework infers speech factors in a sequential way, where factors previously inferred are used as conditional variables when inferring other factors. We will show that this approach can effectively factorize speech signals, and using these factors, the original speech spectrum can be recovered with a high accuracy. This factorization and reconstruction approach provides potential values for many speech processing tasks, e.g., speaker recognition and emotion recognition, as will be demonstrated in the paper.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/27/2020

Deep generative factorization for speech signal

Various information factors are blended in speech signals, which forms t...
10/29/2019

On Investigation of Unsupervised Speech Factorization Based on Normalization Flow

Speech signals are complex composites of various information, including ...
03/31/2016

Multi-task Recurrent Model for Speech and Speaker Recognition

Although highly correlated, speech and speaker recognition have been reg...
10/23/2022

Speaker Identification from emotional and noisy speech data using learned voice segregation and Speech VGG

Speech signals are subjected to more acoustic interference and emotional...
05/13/2023

Vocal Style Factorization for Effective Speaker Recognition in Affective Scenarios

The accuracy of automated speaker recognition is negatively impacted by ...
01/21/2016

On Structured Sparsity of Phonological Posteriors for Linguistic Parsing

The speech signal conveys information on different time scales from shor...

Please sign up or login with your details

Forgot password? Click here to reset