Back to Search

Hybrid nearest-neighbor/cluster adaptive training for rapid speaker adaptation in statistical speech synthesis systems

Title	Hybrid nearest-neighbor/cluster adaptive training for rapid speaker adaptation in statistical speech synthesis systems
Author	Mohammadi, Amir, Demiroğlu, Cenk
Publication Date:	2013
Publication Place	- International Speech Communication Association
Subject	Statistical speech synthesis, Speaker adaptation, Cluster adaptive training, Eigenvoice adaptation
Type	Document
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	9781629934433
Record ID	e72da822-5be8-4963-b726-475b4a5ce556
Library Location	Electrical & Electronics Engineering
Date	2013
Notes	Due to copyright restrictions, the access to the full text of this article is only available via subscription.
Sample Text	Statistical speech synthesis (SSS) approach has become one of the most popular methods in the speech synthesis field. An advantage of the SSS approach is the ability to adapt to a target speaker with a couple of minutes of adaptation data. However, many applications, especially in consumer electronics, require adaptation with only a few seconds of data which can be done using eigenvoice adaptation techniques. Although such techniques work well in speech recognition, they are known to generate perceptual artifacts in statistical speech synthesis. Here, we propose two methods to both alleviate those quality problems and improve the speaker similarity obtained with the baseline eigenvoice adaptation algorithm. Our first method is based on using a Bayesian approach for constraining the eigenvoice adaptation algorithm to move in realistic directions in the speaker space to reduce artifacts. Our second method is based on finding a reference speaker that is close to the target speaker, and using that reference speaker as the seed model in a second eigenvoice adaptation step. Both techniques performed significantly better than the baseline eigenvoice method in the subjective quality and similarity tests.

View in source Özyeğin University Özyeğin University - Ottoman library catalog search

Özyeğin University

Hybrid nearest-neighbor/cluster adaptive training for rapid speaker adaptation in statistical speech synthesis systems

Author Mohammadi, Amir, Demiroğlu, Cenk

Publication Date 2013

Publication Place - International Speech Communication Association

Subject Statistical speech synthesis, Speaker adaptation, Cluster adaptive training, Eigenvoice adaptation

Type Document

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 9781629934433

Record ID e72da822-5be8-4963-b726-475b4a5ce556

Library Location Electrical & Electronics Engineering

Date 2013

Notes Due to copyright restrictions, the access to the full text of this article is only available via subscription.

Sample Text Statistical speech synthesis (SSS) approach has become one of the most popular methods in the speech synthesis field. An advantage of the SSS approach is the ability to adapt to a target speaker with a couple of minutes of adaptation data. However, many applications, especially in consumer electronics, require adaptation with only a few seconds of data which can be done using eigenvoice adaptation techniques. Although such techniques work well in speech recognition, they are known to generate perceptual artifacts in statistical speech synthesis. Here, we propose two methods to both alleviate those quality problems and improve the speaker similarity obtained with the baseline eigenvoice adaptation algorithm. Our first method is based on using a Bayesian approach for constraining the eigenvoice adaptation algorithm to move in realistic directions in the speaker space to reduce artifacts. Our second method is based on finding a reference speaker that is close to the target speaker, and using that reference speaker as the seed model in a second eigenvoice adaptation step. Both techniques performed significantly better than the baseline eigenvoice method in the subjective quality and similarity tests.