yr 〜
yr

Search results 4

DPGMM-RNN Hybrid Model: Towards Universal Acoustic Modeling to ASR at Different Supervised Levels

DPGMM-RNN Hybrid Model: Towards Universal Acoustic Modeling to ASR at Different Supervised Levels
Digital博士論文障害者向け資料あり
Wu, BinNara Institute of Science and Technology2022-03-31
Available onlineNational Diet LibraryOther Libraries in Japan
  • Subject HeadingDirichlet process Gaussian mixture model (DPGMM) recurrent neura...

Statistical waveform modification for speaking and singing voice conversion

Statistical waveform modification for speaking and singing voice conversion
Digital博士論文障害者向け資料あり
Kobayashi, KazuhiroNara Institute of Science and Technology2017-03-24
Available onlineNational Diet LibraryOther Libraries in Japan
  • Subject Heading... individuality Gaussian mixture model

Acoustic modeling and speech parameter generation for high-quality statistical parametric speech synthesis

Acoustic modeling and speech parameter generation for high-quality statistical parametric speech synthesis
Digital博士論文障害者向け資料あり
Takamichi, ShinnosukeNara Institute of Science and Technology2016-03-24
Available onlineNational Diet LibraryOther Libraries in Japan
  • Subject Heading...n Markov model Gaussian mixture model acoustic modeling

Techniques for Improving Voice Conversion Based on Eigenvoices

Techniques for Improving Voice Conversion Based on Eigenvoices
Digital博士論文
大谷, 大和Nara Institute of Science and Technology2010-03-24
Other Libraries in Japan
  • Subject Headingspeech synthesis voice conversion Gaussian mixture model eigenvoice many-to-many

Reached to the end of result.