Skip to content

Publications

Publications (1st author)

  • Li, Xinjian, et al. "Question Answering System for Entrance Exams in QA4MRE." CLEF (Working Notes). 2013

  • Dalmia, S*, Li, X* et al. "Domain robust feature extraction for rapid low resource asr development." 2018 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2018. (* equal contribution)

  • Li, Xinjian, et al. "Multilingual Speech Recognition with Corpus Relatedness Sampling." Proc. Interspeech 2019 (2019): 2120-2124.

  • Li, Xinjian, et al. "SANTLR: Speech Annotation Toolkit for Low Resource Languages." Proc. Interspeech 2019 (2019): 3681-3682.

  • Li, Xinjian, et al. "Towards zero-shot learning for automatic phonemic transcription." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34. No. 05. 2020.

  • Li, Xinjian, et al. "Universal phone recognition with a multilingual allophone system." ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020. 1

  • Li, Xinjian, et al. "Phone Distribution Estimation for Low Resource Languages." ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021.

  • Li, Xinjian, et al. "Multilingual phonetic dataset for low resource speech recognition." ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021.

  • Li, Xinjian, et al. "Hierarchical Phone Recognition with Compositional Phonetics." Interspeech. 2021.

  • Li, Xinjian, et al. "Zero-shot Learning for Grapheme to Phoneme Conversion with Language Ensemble." Findings of the Association for Computational Linguistics: ACL 2022. 2022. [pdf]

  • Li, Xinjian, et al. "Phone Inventories and Recognition for Every Language" LREC 2022. 2022

  • Li, Xinjian, et al. "ASR2K: Speech Recognition for Around 2000 Languages without Audio" Interspeech 2022. 2022

Publications (others)

  • Li, J., Qu, Sh., Wang, Y., Li, X., Das,S., Metze, F., Music Theory Inspired Policy Gradient Method for Piano Music Transcription NeurIPS 2018 Workshop

  • Yao, J., Li, X., Fiscato, M., Ohtsuki, K., JLM - Fast RNN Language Model with Large Vocabulary. ANLP 2019

  • Yao, J., Shu, R., Li, X., Ohtsuki, K., Nakayama, H., Real-time Neural-Based Input Method NACCL 2019

  • Dalmia, S., Li, X., Black, A. W., Metze, F., Phoneme Level Language Models for Sequence Based Low Resrouce ASR ICASSP 2019

  • Li, S Qu, X Li, J Szurley, JZ Kolter, F Metze. Adversarial Music: Real World Audio Adversary Against Wake-word Detection System NeurIPS 2019

  • Dong, Fengquan, et al. "Machine listening for heart status monitoring: Introducing and benchmarking hss—the heart sounds shenzhen corpus." IEEE journal of biomedical and health informatics 24.7 (2019): 2082-2092.

  • Mortensen, David R., et al. "AlloVera: A Multilingual Allophone Database." Proceedings of the 12th Language Resources and Evaluation Conference. 2020.

  • Neubig, Graham, et al. "A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization." LREC 2020 Workshop Language Resources and Evaluation Conference 11–16 May 2020.

  • Qiu, Zimeng, et al. "Towards Context-Aware End-to-End Code-Switching Speech Recognition." Proc. Interspeech 2020 (2020): 4776-4780.

  • Huang, Wen-Chin, et al. "On Prosody Modeling for ASR+ TTS based Voice Conversion." 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). IEEE, 2021.

  • Gupta, Akshat, et al. "Acoustics based intent recognition using discovered phonetic units for low resource languages." ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021.

  • Siminyu, Kathleen, et al. "Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties." Interspeech. 2021.

  • Mortensen, David R., et al. "Tusom2021: A phonetically transcribed speech dataset from an endangered language for universal phone recognition experiments." Interspeech. 2021.

  • Li, Juncheng B., et al. "On adversarial robustness of large-scale audio visual learning." ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022. (Best Student Paper)

  1. Xinjian Li, Siddharth Dalmia, Juncheng Li, Matthew Lee, Patrick Littell, Jiali Yao, Antonios Anastasopoulos, David R Mortensen, Graham Neubig, Alan W Black, and others. Universal phone recognition with a multilingual allophone system. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 8249–8253. IEEE, 2020. ↩