An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis

Takaki, Shinji; Oura, Keiichiro; Nankaku, Yoshihiko; Tokuda, Keiichi

doi:10.1109/icassp.2011.5947404

Cited by 2 publications

(2 citation statements)

References 9 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MOS for natural speech was about 4.7, so none of the systems achieved similar naturalness to the human voice. In addition, speech synthesized by Japanese methods developed within the past two years was evaluated [10], [11]. In these tests, none of the systems achieved similar naturalness to the human voice.…”

Section: Naturalness Of Conventionalmentioning

confidence: 99%

An Automatic Broadcast System for a Weather Report Radio Program

Segi¹,

Takou²,

Seiyama³

et al. 2013

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

Here we describe a speech-synthesis method using templates that can generate recording-sentence sets for speech databases and produce natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the recording-sentence set required to just a fraction of that needed by a comparable method. After integrating the recording voice of the generated recording-sentence set into the speech database, speech was produced by a voice synthesizer using templates. In a paired-comparison test, 66 % of the speech samples synthesized by our system using templates were preferred to those produced by a conventional voice synthesizer. In an evaluation test using a five-point mean opinion score (MOS) scale, the speech samples synthesized by our system scored 4.97, whereas the maximum score for commercially available voice synthesizers was 3.09. In addition, we developed an automatic broadcast system for the weather report program using the speech-synthesis method and speech-rate converter. The system was evaluated using real weather data for more than 1 year, and exhibited sufficient stability and synthesized speech quality for broadcast purposes.

show abstract

Section: Naturalness Of Conventionalmentioning

confidence: 99%

An Automatic Broadcast System for a Weather Report Radio Program

Segi¹,

Takou²,

Seiyama³

et al. 2013

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

show abstract

“…This method has several advantages as it is easy to use for voice conversion, has good performance with small speech databases, and does not require a high-performance Central Processing Unit (CPU) or large memory. However, the naturalness of the speech synthesized using this method is not so high (Zen, 2008;Takaki, 2011;Nose, 2013).…”

Section: Introductionmentioning

confidence: 99%

Unit-Selection Speech Synthesis Method Using Words as Search Units

Segi

2016

International Journal of Multimedia Data Engineering and Management

View full text Add to dashboard Cite

Unit-selection speech-synthesis systems have been proposed. In most of the unit-selection speech-synthesis systems, search units are rather short such as syllables, phonemes and diphones. However, when applied to large speech databases, shorter units produce more voice-waveform candidates and a larger speech database cannot be used without narrow pruning for practical use. Narrow pruning impairs the quality of the synthesized speech. Here the author examined the possibility of using words as search units. Subjective evaluations indicated that 70% of the speech synthesized by the proposed method sounded more natural than that synthesized by a conventional method. The five-point mean opinion score of the synthesized speech was 3.5, and 21% was judged to sound as natural as human speech. These results demonstrate the effectiveness of unit-selection speech synthesis using words as search units.

show abstract

An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis

Cited by 2 publications

References 9 publications

An Automatic Broadcast System for a Weather Report Radio Program

An Automatic Broadcast System for a Weather Report Radio Program

Unit-Selection Speech Synthesis Method Using Words as Search Units

Contact Info

Product

Resources

About