Paper Info
Title
Hybrid Voice Conversion of Unit Selection and Generation Using Prosody Dependent HMM
Abstract
We propose a hybrid voice conversion method which employs a combination of techniques using HMM-based unit selection and spectrum generation. In the proposed method, the HMM-based unit selection selects the most likely unit for the required phoneme context from the target speaker's corpus when candidates of the target unit exist in the corpus. Unit selection is performed based on the sequence of the spectral probability distribution obtained from the adapted HMMs. On the other hand, when a target unit does not exist in a corpus, a target waveform is generated from the adapted HMM sequence by maximizing the spectral likelihood. The proposed method also employs the HMM in which the spectral probability distribution is adjusted to the target prosody using the weight defined by the prosodic probability of each distribution. To show the effectiveness of the proposed method, sound quality and speaker individuality tests were conducted. The results revealed that the proposed method could produce high-quality speech and individuality of the synthesized sound was more similar to the target speaker compared to conventional methods.
Year
DOI
Venue
2006
10.1093/ietisy/e89-d.11.2775
IEICE Transactions
Keywords
Field
DocType
unit selection,likely unit,conventional method,target unit,spectral probability distribution,hmm-based unit selection,target prosody,prosody dependent hmm,hybrid voice conversion,target waveform,target speaker,hmm,speech synthesis
Prosody,Audio signal,Speech synthesis,Pattern recognition,Computer science,Waveform,Sound quality,Speech recognition,Probability distribution,Artificial intelligence,Hidden Markov model,Linear regression
Journal
Volume
Issue
ISSN
E89-D
11
1745-1361
Citations 
PageRank 
References 
6
0.62
0
Authors
3
Name
Order
Citations
PageRank
Tadashi Okubo160.95
Ryo Mochizuki2184.49
Tetsunori Kobayashi341388.35