Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations
원문 초록
Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks. Aggregating these speech representations across time is typically approached by using descriptive statistics, and in particular, using the first- and second-order statistics of representation coefficients. In this paper, we examine an alternative way of extracting speaker and emotion information from self-supervised trained models, based on the correlations between the coefficients of the representations - correlation pooling. We show improvements over mean pooling and further gains when the pooling methods are combined via fusion. The code is available at github.com/Lamomal/s3prl_correlation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
JEPA4Rec: Learning Effective Language Representations for Sequential Recommendation via Joint Embedding Predictive Architecture
Describe Anything Model for Visual Question Answering on Text-rich Images
Assay2Mol: large language model-based drug design using BioAssay context
Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor
Dataset Distillation via Vision-Language Category Prototype
RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.