Thousands of Voices for HMM-Based Speech Synthesis-Analysis and Application of TTS Systems Built on Various ASR Corpora

Junichi Yamagishi, Bela Usabaev, Simon King, Oliver Watts, John Dines, Jilei Tian, Yong Guan, Rile Hu, Keiichiro Oura, Yi-Jian Wu, Keiichi Tokuda, Reima Karhila, Mikko Kurimo

Research output: Contribution to journalArticlepeer-review

Abstract

In conventional speech synthesis, large amounts of phonetically balanced speech data recorded in highly controlled recording studio environments are typically required to build a voice. Although using such data is a straightforward solution for high quality synthesis, the number of voices available will always be limited, because recording costs are high. On the other hand, our recent experiments with HMM-based speech synthesis systems have demonstrated that speaker-adaptive HMM-based speech synthesis (which uses an "average voice model" plus model adaptation) is robust to non-ideal speech data that are recorded under various conditions and with varying microphones, that are not perfectly clean, and/or that lack phonetic balance. This enables us to consider building high-quality voices on "non-TTS" corpora such as ASR corpora. Since ASR corpora generally include a large number of speakers, this leads to the possibility of producing an enormous number of voices automatically. In this paper, we demonstrate the thousands of voices for HMM-based speech synthesis that we have made from several popular ASR corpora such as the Wall Street Journal (WSJ0, WSJ1, and WSJCAM0), Resource Management, Globalphone, and SPEECON databases. We also present the results of associated analysis based on perceptual evaluation, and discuss remaining issues.
Original languageEnglish
Pages (from-to)984-1004
Number of pages21
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume18
Issue number5
DOIs
Publication statusPublished - Jul 2010

Keywords

  • hidden Markov models
  • speaker recognition
  • speech synthesis
  • Automatic speech recognition (ASR)
  • H Triple S (HTS)
  • SPEECON database
  • WSJ database
  • average voice
  • hidden Markov model (HMM)-based speech synthesis
  • speaker adaptation
  • voice conversion

Fingerprint Dive into the research topics of 'Thousands of Voices for HMM-Based Speech Synthesis-Analysis and Application of TTS Systems Built on Various ASR Corpora'. Together they form a unique fingerprint.

Cite this