Rapid Connectionist Speaker Adaptation

11/15/2022
by   Michael Witbrock, et al.
0

We present SVCnet, a system for modelling speaker variability. Encoder Neural Networks specialized for each speech sound produce low dimensionality models of acoustical variation, and these models are further combined into an overall model of voice variability. A training procedure is described which minimizes the dependence of this model on which sounds have been uttered. Using the trained model (SVCnet) and a brief, unconstrained sample of a new speaker's voice, the system produces a Speaker Voice Code that can be used to adapt a recognition system to the new speaker without retraining. A system which combines SVCnet with an MS-TDNN recognizer is described

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/04/2018

Voice Imitating Text-to-Speech Neural Networks

We propose a neural text-to-speech (TTS) model that can imitate a new sp...
research
10/25/2021

Controllable and Interpretable Singing Voice Decomposition via Assem-VC

We propose a singing decomposition system that encodes time-aligned ling...
research
11/27/2018

Large-scale Speaker Retrieval on Random Speaker Variability Subspace

This paper describes a fast speaker search system to retrieve segments o...
research
11/08/2018

Who Do I Sound Like? Showcasing Speaker Recognition Technology by YouTube Voice Search

The popularization of science can often be disregarded by scientists as ...
research
05/22/2023

Can we hear physical and social space together through prosody?

When human listeners try to guess the spatial position of a speech sourc...
research
08/20/2020

asya: Mindful verbal communication using deep learning

asya is a mobile application that consists of deep learning models which...
research
12/27/2018

Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition

In this paper we propose a method to model speaker and session variabili...

Please sign up or login with your details

Forgot password? Click here to reset