Dysarthria Normalization via Local Lie Group Transformations for Robust ASR
We present a geometry-driven method for normalizing dysarthric speech by modeling time, frequency, and amplitude distortions as smooth, local Lie group transformations of spectrograms. Scalar fields generate these deformations via exponential maps, and a neural network is trained - using only synthetically warped healthy speech - to infer the fields and apply an approximate inverse at test time. We introduce a spontaneous-symmetry-breaking (SSB) potential that encourages the model to discover non-trivial field configurations. On real pathological speech, the system delivers consistent gains: up to 17 percentage-point WER reduction on challenging TORGO utterances and a 16 percent drop in WER variance, with no degradation on clean CommonVoice data. Character and phoneme error rates improve in parallel, confirming linguistic relevance. Our results demonstrate that geometrically structured warping provides consistent, zero-shot robustness gains for dysarthric ASR.
Code (1)
Tasks
Robust Speech Recognitionspeech-recognitionSpeech RecognitionZero-shot GeneralizationSimilar Papers 제목 키워드 기반
Learning to detect dysarthria from raw speech
Speech classifiers of paralinguistic traits traditionally learn from diverse hand-crafted low-level features, by selecting the relevant information for the task at hand. We explore an alternative to this selection, by le…
General ClassificationSentencespeech-recognitionSpeech RecognitionGenerating configurations of increasing lattice size with machine learning and the inverse renormalization group
We review recent developments of machine learning algorithms pertinent to the inverse renormalization group, which was originally established as a generative numerical method by Ron-Swendsen-Brandt via the implementation…
An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set im…
Conditional Image GenerationFew-Shot LearningImage GenerationQuestion Answering+2Geometric Clifford Algebra Networks
We propose Geometric Clifford Algebra Networks (GCANs) for modeling dynamical systems. GCANs are based on symmetry group transformations using geometric (Clifford) algebras. We first review the quintessence of modern (pl…
Inverse renormalization group of spin glasses
We propose inverse renormalization group transformations to construct approximate configurations for lattice volumes that have not yet been accessed by supercomputers or large-scale simulations in the study of spin glass…