Topological Data Analysis for Speech Processing
원문 초록
We apply topological data analysis (TDA) to speech classification problems and to the introspection of a pretrained speech model, HuBERT. To this end, we introduce a number of topological and algebraic features derived from Transformer attention maps and embeddings. We show that a simple linear classifier built on top of such features outperforms a fine-tuned classification head. In particular, we achieve an improvement of about $9\%$ accuracy and $5\%$ ERR on four common datasets; on CREMA-D, the proposed feature set reaches a new state of the art performance with accuracy $80.155$. We also show that topological features are able to reveal functional roles of speech Transformer heads; e.g., we find the heads capable to distinguish between pairs of sample sources (natural/synthetic) or voices without any downstream fine-tuning. Our results demonstrate that TDA is a promising new approach for speech analysis, especially for tasks that require structural prediction. Appendices, an introduction to TDA, and other additional materials are available here - https://topohubert.github.io/speech-topology-webpages/
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Comparing the Effects of Persistence Barcodes Aggregation and Feature Concatenation on Medical Imaging
Topological Machine Learning for Protein-Nucleic Acid Binding Affinity Changes Upon Mutation
Topology across Scales on Heterogeneous Cell Data
Short-PHD: Detecting Short LLM-generated Text with Topological Data Analysis After Off-topic Content Insertion
A Topological Data Analysis Framework for Quantifying Necrosis in Glioblastomas
Persistent Homology-induced Graph Ensembles for Time Series Regressions
토론
이 논문과 연결된 포럼 글이 아직 없습니다.