Sotabase

Career

· Research Intern, MIT Sussman Lab2023–
· Research Assistant, MIT CSAIL2022–

Publications (17)

Distilhubert: Speech Representation Learning by Layer-Wise Distillation of Hidden-Unit Bert
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2021
206
cited
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
Annual Meeting of the Association for Computational Linguistics · 2022
124
cited
A Large-Scale Evaluation of Speech Foundation Models
IEEE/ACM Transactions on Audio Speech and Language Processing · 2024
56
cited
SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model
Spoken Language Technology Workshop · 2022
41
cited
Towards Lifelong Learning of End-to-end ASR
Interspeech · 2021
38
cited
DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning
Neural Information Processing Systems · 2023
37
cited
Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering
Interspeech · 2023
31
cited
End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training
Spoken Language Technology Workshop · 2020
18
cited
Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models
arXiv.org · 2021
18
cited
Non-Autoregressive Mandarin-English Code-Switching Speech Recognition
Automatic Speech Recognition & Understanding · 2021
16
cited
M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2022
11
cited
COLLD: Contrastive Layer-to-Layer Distillation for Compressing Multilingual Pre-Trained Speech Encoders
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2023
8
cited
R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces
North American Chapter of the Association for Computational Linguistics · 2023
8
cited
DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
Interspeech · 2024
6
cited
SpeechCLIP+: Self-Supervised Multi-Task Representation Learning for Speech Via Clip and Speech-Image Data
2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · 2024
6
cited
USAD: Universal Speech and Audio Representation via Distillation
arXiv.org · 2025
3
cited
End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Layer-wise Transfer Learning
arXiv.org · 2020
2
cited
Sotabase
Heng-Jui Chang | Researcher Profile | Sotabase | Sotabase