2. Material on project topics

2.25. Pronunciation model adaptation

  • Bisani, M., & Ney, H. (2008). Joint-sequence models for grapheme-to-phoneme conversion. Speech communication, 50(5), 434-451.
  • Maas, A., Xie, Z., Jurafsky, D., & Ng, A. (2015). Lexicon-free conversational speech recognition with neural networks. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 345-354).
  • Tools: Sequitar G2P
  • Materials: WSJ_5k (from exercise 4)