Streaming end-to-end speech recognition for mobile devices Y He, TN Sainath, R Prabhavalkar, I McGraw, R Alvarez, D Zhao, ... ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 736 | 2019 |
A Streaming On-device End-to-end Model Surpassing Server-side Conventional Model Quality And Latency TN Sainath, Y He, B Li, A Narayanan, R Pang, A Bruguier, S Chang, W Li, ... ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 226 | 2020 |
Contextualized streaming end-to-end speech recognition with trie-based deep biasing and shallow fusion D Le, M Jain, G Keren, S Kim, Y Shi, J Mahadeokar, J Chan, ... arXiv preprint arXiv:2104.02194, 2021 | 82 | 2021 |
Prompting large language models with speech recognition abilities Y Fathullah, C Wu, E Lakomkin, J Jia, Y Shangguan, K Li, J Guo, W Xiong, ... ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 79 | 2024 |
Optimizing Speech Recognition For The Edge Y Shangguan, J Li, Q Liang, R Alvarez, I McGraw Third Conference on Machine Learning and Systems, On-device Intelligence …, 2019 | 71 | 2019 |
Alignment restricted streaming recurrent neural network transducer J Mahadeokar, Y Shangguan, D Le, G Keren, H Su, T Le, CF Yeh, ... 2021 IEEE Spoken Language Technology Workshop (SLT), 52-59, 2021 | 69 | 2021 |
Efficient Knowledge Distillation for RNN-Transducer Models S Panchapagesan, DS Park, CC Chiu, Y Shangguan, Q Liang, ... ICASSP 2021, 2020 | 54 | 2020 |
UMEME: University of Michigan emotional McGurk effect data set EM Provost, Y Shangguan, C Busso IEEE Transactions on Affective Computing 6 (4), 395-409, 2015 | 35 | 2015 |
Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer S Kim, Y Shangguan, J Mahadeokar, A Bruguier, C Fuegen, ML Seltzer, ... ICASSP 2021, arXiv preprint arXiv:2010.13878, 2020 | 26 | 2020 |
Dissecting the User Perceived Latency of On-Device E2E Speech Recognition Y Shangguan, R Prabhavalkar, H Su, J Mahadeokar, Y Shi, J Zhou, C Wu, ... Submitted to Interspeech 2021, https://arxiv.org/abs/2104.02207, 2021 | 25 | 2021 |
Omni-sparsity dnn: Fast sparsity optimization for on-device streaming e2e asr via supernet H Yang, Y Shangguan, D Wang, M Li, P Chuang, X Zhang, G Venkatesh, ... ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 13 | 2022 |
Streaming transformer transducer based speech recognition using non-causal convolution Y Shi, C Wu, D Wang, A Xiao, J Mahadeokar, X Zhang, C Liu, K Li, ... ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 13 | 2022 |
Memory-efficient Speech Recognition on Smart Devices G Venkatesh, A Valliappan, J Mahadeokar, Y Shangguan, C Fuegen, ... ICASSP 2021, arXiv preprint arXiv:2102.11531, 2021 | 13 | 2021 |
Federated domain adaptation for asr with full self-supervision J Jia, J Mahadeokar, W Zheng, Y Shangguan, O Kalinli, F Seide arXiv preprint arXiv:2203.15966, 2022 | 12 | 2022 |
Multi-head state space model for speech recognition Y Fathullah, C Wu, Y Shangguan, J Jia, W Xiong, J Mahadeokar, C Liu, ... arXiv preprint arXiv:2305.12498, 2023 | 10 | 2023 |
Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer Y Shangguan, K Knister, Y He, I McGraw, F Beaufays Proc. Interspeech 2020, 591--595, 2020 | 10 | 2020 |
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs Y Fathullah, C Wu, E Lakomkin, K Li, J Jia, Y Shangguan, J Mahadeokar, ... Proceedings of the 2024 Conference of the North American Chapter of the …, 2024 | 9 | 2024 |
Learning a dual-mode speech recognition model via self-pruning C Liu, Y Shangguan, H Yang, Y Shi, R Krishnamoorthi, O Kalinli 2022 IEEE Spoken Language Technology Workshop (SLT), 273-279, 2023 | 9 | 2023 |
EmoShapelets: Capturing Local Dynamics of Audio-visual Affective Speech Y Shangguan, E Mower Provost Proc. of International Conference on Affective Computing and Intelligent …, 2015 | 8 | 2015 |
Adaptive beam pruning for automatic speech recognition DS Filimonov, Y Shangguan US Patent 10,199,037, 2019 | 5 | 2019 |