Polyglot Speech Synthesis Based on Cross-Lingual Frame Selection Using Auditory and Articulatory Features

@article{Chen2014PolyglotSS,
  title={Polyglot Speech Synthesis Based on Cross-Lingual Frame Selection Using Auditory and Articulatory Features},
  author={Chia-Ping Chen and Yi-Chin Huang and Chung-Hsien Wu and K. Lee},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year={2014},
  volume={22},
  pages={1558-1570}
}
In this paper, an approach for polyglot speech synthesis based on cross-lingual frame selection is proposed. This method requires only mono-lingual speech data of different speakers in different languages for building a polyglot synthesis system, thus reducing the burden of data collection. Essentially, a set of artificial utterances in the second language for a target speaker is constructed based on the proposed cross-lingual frame-selection process, and this data set is used to adapt a… Expand
12 Citations
Polyglot Speech Synthesis: A Review
  • 3
Candidate Expansion and Prosody Adjustment for Natural Speech Synthesis Using a Small Corpus
  • 1
Speaker Adaptation of a Multilingual Acoustic Model for Cross-Language Synthesis
  • 2
Multilingual Text-to-Speech Software Component for Dynamic Language Identification and Voice Switching
  • 1
  • PDF
A survey on speech synthesis techniques in Indian languages
  • 2
...
1
2
...

References

Spectral voice conversion for text-to-speech synthesis
  • A. Kain, Michael W. Macon
  • Computer Science
  • Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)
  • 1998
  • 666
  • Highly Influential
  • PDF