Optimization of cost function weights for unit selection speech synthesis using speech recognition

Title:

Optimization of cost function weights for unit selection speech synthesis using speech recognition

Creator:

Pobar, Miran, Martinčić-Ipšić, Sanda, and Ipšić, Ivo

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:bfe7da79-7f4c-465c-982c-cd4e2db0495b
uuid:bfe7da79-7f4c-465c-982c-cd4e2db0495b
doi:10.14311/NNW.2012.22.026

Subject:

Speech synthesis, statistical parametrical synthesis, unit selection, and weight tuning

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

A well known problem in unit selection speech synthesis is designing the join and target function sub-costs and optimizing their corresponding weights so that they reflect the human listeners' preferences. To achieve this we propose a procedure where an objective criterion for optimal speech unit selection is used. The objective criterion for tuning the cost function weights is based on automatic speech recognition results. In order to demonstrate the effectiveness of the proposed method listening tests with 31 naive listeners were performed. The experimental results have shown that the proposed method improves speech quality and intelligibility. In order to evaluate the quality of synthesized speech the unit selection speech synthesis system is compared with two other Croatian speech synthesis systems with voices built using the same recorded speech corpus. One of these voices was built with the Festival speech synthesis system using the statistical parametric method and the other is a diphone concatenation based text-to-speech system. The comparison is based on subjective tests using MOS (mean opinion score) evaluation. The system using the proposed method used for cost function weights optimization performs better than other compared systems according to the subjective tests.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2012 Volume:22 | Number:5

Harvested from:

CDK

Metadata only:

false