GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
CoRR, 2024
DOC-RAG: ASR Language Model Personalization with Domain-Distributed Co-occurrence Retrieval Augmentation.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024
PersonaLM: Language Model Personalization via Domain-distributed Span Aggregated K-Nearest N-gram Retrieval Augmentation.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
LET-Decoder: A WFST-Based Lazy-Evaluation Token-Group Decoder With Exact Lattice Generation.
IEEE Signal Process. Lett., 2021
Private Language Model Adaptation for Speech Recognition.
CoRR, 2021
speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation Assessment.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021
A Parallelizable Lattice Rescoring Strategy with Neural Language Models.
Proceedings of the IEEE International Conference on Acoustics, 2021
The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge.
CoRR, 2020
Neural Language Modeling with Implicit Cache Pointers.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020
Efficient MDI Adaptation for n-Gram Language Models.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020
An Empirical Study of Transformer-Based Neural Language Model Adaptation.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020
Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks.
Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018
Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition.
Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018
Neural Network Language Modeling with Letter-Based Features and Importance Sampling.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018
A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018
A Time-Restricted Self-Attention Layer for ASR.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018