Follow
Qiujia Li
Qiujia Li
Research Scientist, Google
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Discriminative neural clustering for speaker diarisation
Q Li, FL Kreyssig, C Zhang, PC Woodland
SLT, 574-581, 2021
472021
Confidence estimation for attention-based sequence-to-sequence models for speech recognition
Q Li, D Qiu, Y Zhang, B Li, Y He, PC Woodland, L Cao, T Strohman
ICASSP, 6388-6392, 2021
432021
Generative modeling of audible shapes for object perception
Z Zhang, J Wu, Q Li, Z Huang, J Traer, JH McDermott, JB Tenenbaum, ...
ICCV, 1251-1260, 2017
412017
Confidence estimation and deletion prediction using bidirectional recurrent neural networks
A Ragni, Q Li, MJF Gales, Y Wang
SLT, 204-211, 2018
372018
Bi-directional lattice recurrent neural networks for confidence estimation
Q Li, PM Ness, A Ragni, MJF Gales
ICASSP, 6755-6759, 2019
322019
Learning word-level confidence for subword end-to-end ASR
D Qiu, Q Li, Y He, Y Zhang, B Li, L Cao, R Prabhavalkar, D Bhatia, W Li, ...
ICASSP, 6393-6397, 2021
292021
Shape and material from sound
Z Zhang, Q Li, Z Huang, J Wu, JB Tenenbaum, WT Freeman
NIPS, 1278-1288, 2017
292017
Integrating source-channel and attention-based sequence-to-sequence models for speech recognition
Q Li, C Zhang, PC Woodland
ASRU, 39-46, 2019
202019
Knowledge distillation for neural transducers from large self-supervised pre-trained models
X Yang, Q Li, PC Woodland
ICASSP, 8527-8531, 2022
182022
Multi-task learning for end-to-end ASR word and utterance confidence with deletion prediction
D Qiu, Y He, Q Li, Y Zhang, L Cao, I McGraw
Interspeech, 4074-4078, 2021
132021
Residual energy-based models for end-to-end speech recognition
Q Li, Y Zhang, B Li, L Cao, PC Woodland
Interspeech, 4069-4073, 2021
132021
PyHTK: Python library and ASR pipelines for HTK
C Zhang, FL Kreyssig, Q Li, PC Woodland
ICASSP, 6470-6474, 2019
122019
Improving confidence estimation on out-of-domain data for end-to-end speech recognition
Q Li, Y Zhang, D Qiu, Y He, L Cao, PC Woodland
ICASSP, 6537-6541, 2022
92022
Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring
Q Li, C Zhang, PC Woodland
Speech Communication 147, 12-21, 2023
72023
Combining frame-synchronous and label-synchronous systems for speech recognition
Q Li, C Zhang, PC Woodland
arXiv preprint arXiv:2107.00764, 2021
42021
Modular domain adaptation for Conformer-based streaming ASR
Q Li, B Li, D Hwang, TN Sainath, PM Mengibar
arXiv preprint arXiv:2305.13408, 2023
32023
Knowledge distillation from multiple foundation models for end-to-end speech recognition
X Yang, Q Li, C Zhang, PC Woodland
arXiv preprint arXiv:2303.10917, 2023
32023
Learning word-level confidence for subword end-to-end automatic speech recognition
D Qiu, Q Li, Y He, Y Zhang, B Li, L Cao, R Prabhavalkar, D Bhatia, W Li, ...
US Patent App. 17/182,592, 2022
32022
Increasing context for estimating confidence scores in automatic speech recognition
A Ragni, MJF Gales, O Rose, K Knill, A Kastanos, Q Li, P Ness
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022
22022
Inverting audio-visual simulation for shape and material perception
Z Zhang, J Wu, Q Li, Z Huang, JB Tenenbaum, WT Freeman
CVPR Workshops, 2536-2538, 2018
22018
The system can't perform the operation now. Try again later.
Articles 1–20