Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Hexin Liu

Hexin Liu

Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Oct 26, 2022
Hexin Liu, Haihua Xu, Leibny Paola Garcia, Andy W. H. Khong, Yi He, Sanjeev Khudanpur

Figure 1 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Figure 2 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Figure 3 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Figure 4 for Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Oct 06, 2022
Shuyue Stella Li, Xiangyu Zhang, Shu Zhou, Hongchao Shu, Ruixing Liang, Hexin Liu, Leibny Paola Garcia

Figure 1 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Figure 2 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Figure 3 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Figure 4 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

* 5 pages, 3 figures, 3 tables

Access Paper or Ask Questions

PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification

Mar 31, 2022
Hexin Liu, Leibny Paola Garcia Perera, Andy W. H. Khong, Suzy J. Styles, Sanjeev Khudanpur

Figure 1 for PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification

Figure 2 for PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification

Figure 3 for PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification

Figure 4 for PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification

* Submitted to Interspeech 2022, updated to the submitted version

Access Paper or Ask Questions

Enhance Language Identification using Dual-mode Model with Knowledge Distillation

Mar 07, 2022
Hexin Liu, Leibny Paola Garcia Perera, Andy W. H. Khong, Justin Dauwels, Suzy J. Styles, Sanjeev Khudanpur

Figure 1 for Enhance Language Identification using Dual-mode Model with Knowledge Distillation

Figure 2 for Enhance Language Identification using Dual-mode Model with Knowledge Distillation

Figure 3 for Enhance Language Identification using Dual-mode Model with Knowledge Distillation

Figure 4 for Enhance Language Identification using Dual-mode Model with Knowledge Distillation

* Submitted to Odyssey 2022

Access Paper or Ask Questions