Post-hoc Disentanglement of Textual and Acoustic Features in Pre-trained Speech Encoders

arXiv:2410.03037 · cs.CL, cs.LG, cs.SD, eess.AS · Submitted 2024-10-03 · Read on arXiv

cs.CL, cs.LG, cs.SD, eess.AS

Submitted: 2024-10-03

Updated: 2026-10-19

Comments: Accepted to Transactions of ACL (TACL)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Acoustic Features — 4× in this paper · explained in 1 episode
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Information Bottleneck — 1× in this paper · explained in 3 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering