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

Add to Chrome

Add to Firefox

Picture for Andy W. H. Khong

Andy W. H. Khong

Improving performance of real-time full-band blind packet-loss concealment with predictive network

Nov 10, 2022
Viet-Anh Nguyen, Anh H. T. Nguyen, Andy W. H. Khong

Figure 1 for Improving performance of real-time full-band blind packet-loss concealment with predictive network

Figure 2 for Improving performance of real-time full-band blind packet-loss concealment with predictive network

Figure 3 for Improving performance of real-time full-band blind packet-loss concealment with predictive network

Figure 4 for Improving performance of real-time full-band blind packet-loss concealment with predictive network

* Submitted to ICASSP 2023, 5 pages, 1 figure, 4 tables

Access Paper or Ask Questions

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

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

TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining

Oct 26, 2021
Viet-Anh Nguyen, Anh H. T. Nguyen, Andy W. H. Khong

Figure 1 for TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining

Figure 2 for TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining

Figure 3 for TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining

Figure 4 for TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining

* ICASSP 2022 submitted, 5 pages, 4 figures, 3 tables

Access Paper or Ask Questions

Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures

Feb 02, 2021
Karn Watcharasupat, Anh H. T. Nguyen, Ching-Hui Ooi, Andy W. H. Khong

Figure 1 for Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures

Figure 2 for Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures

Figure 3 for Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures

* (c) 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Access Paper or Ask Questions