| Parallel training of DNNs with natural gradient and parameter averaging D Povey, X Zhang, S Khudanpur arXiv preprint arXiv:1410.7455, 2014 | 409 | 2014 |
| Improving deep neural network acoustic models using generalized maxout networks X Zhang, J Trmal, D Povey, S Khudanpur 2014 IEEE international conference on acoustics, speech and signal …, 2014 | 403 | 2014 |
| Transformer-based acoustic modeling for hybrid speech recognition Y Wang, A Mohamed, D Le, C Liu, A Xiao, J Mahadeokar, H Huang, ... ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 264 | 2020 |
| Scaling speech technology to 1,000+ languages V Pratap, A Tjandra, B Shi, P Tomasello, A Babu, S Kundu, A Elkahky, ... Journal of Machine Learning Research (JMLR), 2024 | 208 | 2024 |
| Improving Speaker Recognition Performance in the Domain Adaptation Challenge using Deep Neural Networks D Garcia-Romero, X Zhang, A McCree, D Povey Proc. SLT, 2014 | 110 | 2014 |
| From senones to chenones: Tied context-dependent graphemes for hybrid speech recognition D Le, X Zhang, W Zheng, C Fügen, G Zweig, ML Seltzer 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019 | 65 | 2019 |
| A KEYWORD SEARCH SYSTEM USING OPEN SOURCE SOFTWARE J Trmal, G Chen, D Povey, S Khudanpur, P Ghahremani, X Zhang, ... Proc. SLT, 2014 | 52 | 2014 |
| Deja-vu: Double feature presentation and iterated loss in deep transformer networks A Tjandra, C Liu, F Zhang, X Zhang, Y Wang, G Synnaeve, S Nakamura, ... ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 48 | 2020 |
| The Kaldi OpenKWS System: Improving Low Resource Keyword Search. J Trmal, M Wiesner, V Peddinti, X Zhang, P Ghahremani, Y Wang, ... Interspeech, 3597-3601, 2017 | 47 | 2017 |
| Towards measuring fairness in speech recognition: Casual conversations dataset transcriptions C Liu, M Picheny, L Sarı, P Chitkara, A Xiao, X Zhang, M Chou, ... ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 35 | 2022 |
| Backstitch: Counteracting Finite-Sample Bias via Negative Steps. Y Wang, V Peddinti, H Xu, X Zhang, D Povey, S Khudanpur Interspeech, 1631-1635, 2017 | 33 | 2017 |
| Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio A Kumar, K Tan, Z Ni, P Manocha, X Zhang, E Henderson, B Xu ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 32 | 2023 |
| Faster, simpler and more accurate hybrid asr systems using wordpieces F Zhang, Y Wang, X Zhang, C Liu, Y Saraf, G Zweig Interspeech 2020, 2020 | 30 | 2020 |
| Multilingual graphemic hybrid ASR with massive data augmentation C Liu, Q Zhang, X Zhang, K Singh, Y Saraf, G Zweig arXiv preprint arXiv:1909.06522, 2019 | 30 | 2019 |
| A diversity-penalizing ensemble training method for deep learning. X Zhang, D Povey, S Khudanpur INTERSPEECH, 3590-3594, 2015 | 27 | 2015 |
| Benchmarking lf-mmi, ctc and rnn-t criteria for streaming asr X Zhang, F Zhang, C Liu, K Schubert, J Chan, P Prakash, J Liu, CF Yeh, ... 2021 IEEE spoken language technology workshop (SLT), 46-51, 2021 | 23 | 2021 |
| Accent-robust automatic speech recognition using supervised and unsupervised wav2vec embeddings J Li, V Manohar, P Chitkara, A Tjandra, M Picheny, F Zhang, X Zhang, ... arXiv preprint arXiv:2110.03520, 2021 | 17 | 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 |
| On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models X Zhang, V Manohar, D Zhang, F Zhang, Y Shi, N Singhal, J Chan, ... 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2021 | 13 | 2021 |
Daniel PoveyChief Speech Scientist, Xiaomi Corp.Verified email at xiaomi.com
