TTS for Low Resource Languages: A Bangla Synthesizer
Alexander Gutkin, Linne Ha, Martin Jansche, Knot Pipatsrisawat, Richard Sproat
Abstract
We present a text-to-speech (TTS) system designed for the dialect of Bengali spoken in Bangladesh. This work is part of an ongoing effort to address the needs of under-resourced languages. We propose a process for streamlining the bootstrapping of TTS systems for under-resourced languages. First, we use crowdsourcing to collect the data from multiple ordinary speakers, each speaker recording small amount of sentences. Second, we leverage an existing text normalization system for a related language (Hindi) to bootstrap a linguistic front-end for Bangla. Third, we employ statistical techniques to construct multi-speaker acoustic models using Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) and Hidden Markov Model (HMM) approaches. We then describe our experiments that show that the resulting TTS voices score well in terms of their perceived quality as measured by Mean Opinion Score (MOS) evaluations.- Anthology ID:
- L16-1317
- Volume:
- Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
- Month:
- May
- Year:
- 2016
- Address:
- Portorož, Slovenia
- Editors:
- Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association (ELRA)
- Note:
- Pages:
- 2005–2010
- Language:
- URL:
- https://aclanthology.org/L16-1317
- DOI:
- Cite (ACL):
- Alexander Gutkin, Linne Ha, Martin Jansche, Knot Pipatsrisawat, and Richard Sproat. 2016. TTS for Low Resource Languages: A Bangla Synthesizer. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2005–2010, Portorož, Slovenia. European Language Resources Association (ELRA).
- Cite (Informal):
- TTS for Low Resource Languages: A Bangla Synthesizer (Gutkin et al., LREC 2016)
- PDF:
- https://preview.aclanthology.org/landing_page/L16-1317.pdf