Probing emergent geometry in speech models via replica theory
The success of deep neural networks in visual tasks have motivated recent theoretical and empirical work to understand how these networks operate. Meanwhile, deep neural networks have also achieved impressive performance in audio processing applications, both as sub-components of larger systems or as complete end-to-end systems. In this work, we employ a recently developed statistical mechanical theory that connects geometric properties of network representations with class separability to probe how information is untangled within neural networks trained to recognize speech. We find that speech recognition models carry out significant layerwise and temporal untangling of words by efficiently extracting task-relevant features. This untangling results from a decrease in the per-class radius and dimension, and a reduction in the correlation between class centers.
Code (0)
등록된 구현이 없습니다.
Tasks
speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Conditional probing: measuring usable information beyond a baseline
Probing experiments investigate the extent to which neural representations make properties -- like part-of-speech -- predictable. One suggests that a representation encodes a property if probing that representation produ…
Word EmbeddingsPerceptual compensation for tonal context in self-supervised speech models
This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chin…
Quantum origin of life: methodological, epistemological and ontological issues
The aim of this essay is to analyze the role of quantum mechanics as an inherent characteristic of life. During the last ten years the problem of the origin of life has become an innovative research subject approached by…
Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations
Self-supervised speech representations can hugely benefit downstream speech technologies, yet the properties that make them useful are still poorly understood. Two candidate properties related to the geometry of the repr…
Machine-Learning Mathematical Structures
We review, for a general audience, a variety of recent experiments on extracting structure from machine-learning mathematical data that have been compiled over the years. Focusing on supervised machine-learning on labele…
BIG-bench Machine Learning