Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System(<Special Section> Statistical Modeling for Speech Processing)

スポンサーリンク

概要

• 論文の詳細を見る

• Development of a hidden Markov model (HMM)-based Korean speech synthesis system and its evaluation is described. Statistical HMM models for Korean speech units are trained with the hand-labeled speech database including the contextual information about phoneme, morpheme, word phrase, utterance, and break strength. The developed system produced speech with a fairly good prosody. The synthesized speech is evaluated and compared with that of our corpus-based unit concatenating Korean text-to-speech system. The two systems were trained with the same manually labeled speech database.

• 社団法人電子情報通信学会の論文
• 2006-03-01

著者

• Hahn Minsoo

  Information And Communications Univ. Seoul Kor

• Kim Sang‐jin

  Information And Communications Univ. Daejeon Kor

• Hahn Minsoo

  Multimedia Group Information And Communications Univ.

• Hahn Minsoo

  Multimedia Group Information And Commun. University

• Kim Sang-jin

  Multimedia Group Information And Communications Univ.

• KIM Jong-Jin

  Spoken Language Processing Team

関連論文

• Implementation and Evaluation of an HMM-Based Korean Speech Synthesis System( Statistical Modeling for Speech Processing)
• Objective Pathological Voice Quality Assessment Based on HOS Features
• Pathological Voice Detection Using Efficient Combination of Heterogeneous Features
• Two-Band Excitation for HMM-Based Speech Synthesis(Speech and Herring)
• New Variable-Bit-Rate Scheme for Waveform Interpolative Coders(Digital Signal Processing)
• A New Speech Enhancement Algorithm for Car Environment Noise Cancellation with MBD and Kalman Filtering(Adaptive Signal Processing and Its Applications)

スポンサーリンク