ouktlab/espnet_streaming_katakana_robustcsj_asr_train_asr_transformer_lm_rnn

ESPnet2 Streaming Katakana ASR model

`ouktlab/espnet_streaming_katakana_robustcsj_asr_train_asr_transformer_lm_rnn`

This model was trained using csj recipe in espnet.

How to use

Citing ESPnet

@inproceedings{watanabe2018espnet,
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  title={{ESPnet}: End-to-End Speech Processing Toolkit},
  year={2018},
  booktitle={Proceedings of Interspeech},
  pages={2207--2211},
  doi={10.21437/Interspeech.2018-1456},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}

or arXiv:

@misc{watanabe2018espnet,
  title={ESPnet: End-to-End Speech Processing Toolkit}, 
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  year={2018},
  eprint={1804.00015},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}

Training data recipe of this model (rev.+bgn.)

@inproceedings{rtakeda2023:apsipa,
  author={Ryu Takeda and Yui Sudo and Kazunori Komatani},
  title={Flexible Evidence Model to Reduce Uncertainty Mismatch Between Speech Enhancement and ASR Based on Encoder-Decoder Architecture},
  year={2023},
  booktitle={Proceedings of Asia Pacific Signal and Information Processing Association (APSIPA)},
  pages={1830-1837}  
}

Katakana model

@inproceedings{rtakeda2024:iwsds,
  author={Ryu Takeda and Kazunori Komatani},
  title={Toward OOV-word Acquisition during Spoken Dialogue using Syllable-based ASR and Word Segmentation},
  year={2024},
  booktitle={Proceedings of International Workshop on Spoken Dialogue Systems Technology (IWSDS)},
}

@inproceedings{oshio2023:apsipa,
  author={Miki Oshio, Hokuto Munakata, Ryu Takeda and Kazunori Komatani},
  title={Out-Of-Vocabulary Word Detection in Spoken Dialogues Based on Joint Decoding with User Response Patterns},
  year={2023},
  booktitle={Proceedings of Asia Pacific Signal and Information Processing Association (APSIPA)},
  pages={1753-1759}  
}

license: cc-by-nc-4.0