 Leveraging Multilingual Self-Supervised Pretrained Models for
Sequence-to-Sequence End-to-End Spoken Language UnderstandingAutomatic Speech Recognition & Understanding (ASRU), 2023 |
 Lego-Features: Exporting modular encoder features for streaming and
deliberation ASRIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
 Lego-MT: Learning Detachable Models for Massively Multilingual Machine
TranslationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Accelerating RNN-T Training and Inference Using CTC guidanceIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 CTC Alignments Improve Autoregressive TranslationConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
