Yamagishi, Junichi

Usabaev, Bela

King, Simon

Watts, O.

Dines, J.

Tian, J.

Hu, R.

Guan, Y.

Oura, K.

Tokuda, K.

Karhila, R.

Kurimo, Mikko

2010-12-20T15:17:29Z

2010-12-20T15:17:29Z

2010

2010-12-20T15:17:30Z

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.

984--1004

10.1109/TASL.2010.2045237

http://dx.doi.org/10.1109/TASL.2010.2045237

http://hdl.handle.net/1842/4551

IEEE

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

Article

5

IEEE Transactions on Audio, Speech and Language Processing

18