Bayesian Parametric and Architectural Domain Adaptation of LF-MMI Trained TDNNs for Elderly and Dysarthric Speech Recognition. J Deng, FR Gutierrez, S Hu, M Geng, X Xie, Z Ye, S Liu, J Yu, X Liu, ... Interspeech, 4818-4822, 2021 | 13 | 2021 |
Improving generalizability of distilled self-supervised speech processing models under distorted settings KP Huang, YK Fu, TY Hsu, FR Gutierrez, FL Wang, LH Tseng, Y Zhang, ... 2022 IEEE Spoken Language Technology Workshop (SLT), 1112-1119, 2023 | 10 | 2023 |
Self-supervised learning with segmental masking for speech representation X Yue, J Lin, FR Gutierrez, H Li IEEE Journal of Selected Topics in Signal Processing 16 (6), 1367-1379, 2022 | 3 | 2022 |
Are Soft Prompts Good Zero-Shot Learners for Speech Recognition? D Ng, C Zhang, R Zhang, Y Ma, F Ritter-Gutierrez, TH Nguyen, C Ni, ... ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 2 | 2024 |
Noise robust distillation of self-supervised speech models via correlation metrics F Ritter-Gutierrez, KP Huang, D Ng, JHM Wong, H Lee, ES Chng, ... arXiv preprint arXiv:2312.12153, 2023 | 1 | 2023 |
Neural Architecture Search for Finding the Best Time Delay Neural Network Acoustic Model for Speech Recognition FAR Gutierrez The University of Edinburgh, 2019 | | 2019 |