On the end-to-end solution to mandarin-english code-switching speech recognition Z Zeng, Y Khassanov, VT Pham, H Xu, ES Chng, H Li arXiv preprint arXiv:1811.00241, 2018 | 99 | 2018 |
Independent language modeling architecture for end-to-end ASR H Xu, Y Khassanov, Z Zeng, ES Chng, C Ni, B Ma, H Li ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 20 | 2020 |
Constrained output embeddings for end-to-end code-switching speech recognition with only monolingual data Y Khassanov, H Xu, VT Pham, Z Zeng, ES Chng, C Ni, B Ma arXiv preprint arXiv:1904.03802, 2019 | 18 | 2019 |
Improving N-gram language modeling for code-switching speech recognition Z Zeng, H Xu, TY Chong, ES Chng, H Li 2017 Asia-Pacific Signal and Information Processing Association Annual …, 2017 | 18 | 2017 |
Leveraging text data using hybrid transformer-LSTM based end-to-end ASR in transfer learning Z Zeng, H Xu, Y Khassanov, ES Chng, C Ni, B Ma 2021 12th International Symposium on Chinese Spoken Language Processing …, 2021 | 14 | 2021 |
Audio codec simulation based data augmentation for telephony speech recognition TL Vu, Z Zeng, H Xu, ES Chng 2019 Asia-Pacific Signal and Information Processing Association Annual …, 2019 | 13 | 2019 |
Enriching rare word representations in neural language models by embedding matrix augmentation Y Khassanov, Z Zeng, VT Pham, H Xu, ES Chng arXiv preprint arXiv:1904.03799, 2019 | 10 | 2019 |
Audio Splicing Localization: Can We Accurately Locate the Splicing Tampering? Z Zeng, Z Wu 2022 13th International Symposium on Chinese Spoken Language Processing …, 2022 | 4 | 2022 |