6 papers · 1 filter
Correlation-Based Distillation Yields More Mergeable Speech-Music Encoders
Fabian Ritter-Gutierrez
A single compact encoder for both speech and music removes the need to maintain a separate model per domain. A practical recipe distils a speech teacher and a music teacher into tw…
What Actually Makes Correlation-Based SSL Distillation Noise-Robust? A Mechanistic Correction
Fabian Ritter-Gutierrez, Nancy F. Chen, Eng Siong Chng
Self-supervised learning (SSL) speech models are accurate but large. Knowledge distillation compresses them, but the student loses the teacher's noise robustness. Correlation-based…
ASTAR-NTU solution to AudioMOS Challenge 2025 Track1
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jui-Chiang Wei +3
Evaluation of text-to-music systems is constrained by the cost and availability of collecting experts for assessment. AudioMOS 2025 Challenge track 1 is created to automatically pr…
A correlation-permutation approach for speech-music encoders model merging
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jeremy H. M Wong +3
Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, dire…
Distilling a speech and music encoder with task arithmetic
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jui-Chiang Wei +4
Despite the progress in self-supervised learning (SSL) for speech and music, existing models treat these domains separately, limiting their capacity for unified audio understanding…
Are Soft Prompts Good Zero-shot Learners for Speech Recognition?
Dianwen Ng, Chong Zhang, Ruixi Zhang +7
Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternati…