Back to Search

Nearest neighbor approach in speaker adaptation for HMM-based speech synthesis

Title	Nearest neighbor approach in speaker adaptation for HMM-based speech synthesis
Author	Mohammadi, Amir, Demiroğlu, Cenk
Publication Date:	2013
Publication Place	- IEEE
Subject	Hidden Markov models, Speech synthesis, Statistical analysis
Type	Document
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	978-1-4673-5561-2
Record ID	91f5927c-3b2b-4bf1-bc3a-7f5fb8146274
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 and successful methods in the speech synthesis field. Smooth speech transitions, without the spurious errors that are observed in unit selection systems, can be generated with the SSS approach. Another advantage 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 adaptation utterances. Here, we propose a rapid adaptation technique that first attempt to select a reference model that is close to the target speaker given a distance measure. Then, as opposed to adapting to target speaker from an average model, as typically done in most systems, adaptation is performed from the new reference model. The proposed system significantly outperformed a state-of-the-art baseline system both in objective and subjective tests especially only when one utterance is available for adaptation.
DOI	10.1109/SIU.2013.6531576

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

Nearest neighbor approach in speaker adaptation for HMM-based speech synthesis

Author Mohammadi, Amir, Demiroğlu, Cenk

Publication Date 2013

Publication Place - IEEE

Subject Hidden Markov models, Speech synthesis, Statistical analysis

Type Document

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 978-1-4673-5561-2

Record ID 91f5927c-3b2b-4bf1-bc3a-7f5fb8146274

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 and successful methods in the speech synthesis field. Smooth speech transitions, without the spurious errors that are observed in unit selection systems, can be generated with the SSS approach. Another advantage 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 adaptation utterances. Here, we propose a rapid adaptation technique that first attempt to select a reference model that is close to the target speaker given a distance measure. Then, as opposed to adapting to target speaker from an average model, as typically done in most systems, adaptation is performed from the new reference model. The proposed system significantly outperformed a state-of-the-art baseline system both in objective and subjective tests especially only when one utterance is available for adaptation.

DOI 10.1109/SIU.2013.6531576