Update README.md

README.md

@@ -41,7 +41,7 @@ Benchmark scores, including our models, can be found at https://rinnakk.github.i
 
 * **Training**
 
-    The model was trained on approximately 19,000 hours of following Japanese speech corpus ReazonSpeech.
+    The model was trained on approximately 19,000 hours of following Japanese speech corpus ReazonSpeech v1.
     Note that speech samples longer than 16 seconds were excluded before training.
     - [ReazonSpeech](https://huggingface.co/datasets/reazon-research/reazonspeech)
 
@@ -128,49 +128,62 @@ The model uses the same sentencepiece-based tokenizer as [japanese-gpt-neox-3.6b
 
 # How to cite
 ```bibtex
-@article{hono2023integration,
-    title={An Integration of Pre-Trained Speech and Language Models for End-to-End Speech Recognition},
-    author={Hono, Yukiya and Mitsuda, Koh and Zhao, Tianyu and Mitsui, Kentaro and Wakatsuki, Toshiaki and Sawada, Kei},
-    journal={arXiv preprint arXiv:2312.03668},
-    year={2023}
+@inproceedings{hono2024integrating,
+    title = {Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition},
+    author = {Hono, Yukiya and Mitsuda, Koh and Zhao, Tianyu and Mitsui, Kentaro and Wakatsuki, Toshiaki and Sawada, Kei},
+    booktitle = {Findings of the Association for Computational Linguistics: ACL 2024},
+    year = {2024}
 }
 
 @misc{rinna-nue-asr,
-    title={rinna/nue-asr},
-    author={Hono, Yukiya and Mitsuda, Koh and Zhao, Tianyu and Mitsui, Kentaro and Wakatsuki, Toshiaki and Sawada, Kei},
-    url={https://huggingface.co/rinna/nue-asr}
+    title = {rinna/nue-asr},
+    author = {Hono, Yukiya and Mitsuda, Koh and Zhao, Tianyu and Mitsui, Kentaro and Wakatsuki, Toshiaki and Sawada, Kei},
+    url = {https://huggingface.co/rinna/nue-asr}
 }
 ```
 ---
 
 # References
 ```bibtex
+@inproceedings{sawada2024release,
+    title = {Release of Pre-Trained Models for the {J}apanese Language},
+    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
+    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
+    month = {5},
+    year = {2024},
+    pages = {13898--13905},
+    url = {https://aclanthology.org/2024.lrec-main.1213},
+    note = {\url{https://arxiv.org/abs/2404.01657}}
+}
+
 @article{hsu2021hubert,
-    title={HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units},
-    author={Hsu, Wei-Ning and Bolte, Benjamin and Tsai, Yao-Hung Hubert and Lakhotia, Kushal and Salakhutdinov, Ruslan and Mohamed, Abdelrahman},
-    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
-    year={2021},
-    volume={29},
-    pages={3451-3460},
-    doi={10.1109/TASLP.2021.3122291}
+    title = {{HuBERT}: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units},
+    author = {Hsu, Wei-Ning and Bolte, Benjamin and Tsai, Yao-Hung Hubert and Lakhotia, Kushal and Salakhutdinov, Ruslan and Mohamed, Abdelrahman},
+    journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
+    month = {10},
+    year = {2021},
+    volume = {29},
+    pages = {3451-3460},
+    doi = {10.1109/TASLP.2021.3122291}
 }
 
 @software{andoniangpt2021gpt,
-    title={{GPT-NeoX: Large Scale Autoregressive Language Modeling in PyTorch}},
-    author={Andonian, Alex and Anthony, Quentin and Biderman, Stella and Black, Sid and Gali, Preetham and Gao, Leo and Hallahan, Eric and Levy-Kramer, Josh and Leahy, Connor and Nestler, Lucas and Parker, Kip and Pieler, Michael and Purohit, Shivanshu and Songz, Tri and Phil, Wang and Weinbach, Samuel},
-    url={https://www.github.com/eleutherai/gpt-neox},
-    doi={10.5281/zenodo.5879544},
-    month={8},
-    year={2021},
-    version={0.0.1},
+    title = {{GPT}-{N}eo{X}: Large Scale Autoregressive Language Modeling in {P}y{T}orch},
+    author = {Andonian, Alex and Anthony, Quentin and Biderman, Stella and Black, Sid and Gali, Preetham and Gao, Leo and Hallahan, Eric and Levy-Kramer, Josh and Leahy, Connor and Nestler, Lucas and Parker, Kip and Pieler, Michael and Purohit, Shivanshu and Songz, Tri and Phil, Wang and Weinbach, Samuel},
+    month = {8},
+    year = {2021},
+    version = {0.0.1},
+    doi = {10.5281/zenodo.5879544},
+    url = {https://www.github.com/eleutherai/gpt-neox}
 }
 
 @inproceedings{aminabadi2022deepspeed,
-    title={{DeepSpeed-Inference}: enabling efficient inference of transformer models at unprecedented scale},
-    author={Aminabadi, Reza Yazdani and Rajbhandari, Samyam and Awan, Ammar Ahmad and Li, Cheng and Li, Du and Zheng, Elton and Ruwase, Olatunji and Smith, Shaden and Zhang, Minjia and Rasley, Jeff and others},
-    booktitle={SC22: International Conference for High Performance Computing, Networking, Storage and Analysis},
-    pages={1--15},
-    year={2022}
+    title = {{DeepSpeed-Inference}: enabling efficient inference of transformer models at unprecedented scale},
+    author = {Aminabadi, Reza Yazdani and Rajbhandari, Samyam and Awan, Ammar Ahmad and Li, Cheng and Li, Du and Zheng, Elton and Ruwase, Olatunji and Smith, Shaden and Zhang, Minjia and Rasley, Jeff and others},
+    booktitle = {SC22: International Conference for High Performance Computing, Networking, Storage and Analysis},
+    pages = {1--15},
+    year = {2022},
+    doi = {10.1109/SC41404.2022.00051}
 }
 ```
 ---