Autoregressive prediction over discrete cochlear tokens yields a speech representation that beats prior self-supervised models on lexical-semantic similarity and is competitive on SUPERB tasks.
Blind phoneme segmentation with temporal prediction errors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Phonemic segmentation of speech is a critical step of speech recognition systems. We propose a novel unsupervised algorithm based on sequence prediction models such as Markov chains and recurrent neural network. Our approach consists in analyzing the error profile of a model trained to predict speech features frame-by-frame. Specifically, we try to learn the dynamics of speech in the MFCC space and hypothesize boundaries from local maxima in the prediction error. We evaluate our system on the TIMIT dataset, with improvements over similar methods.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Representing Speech Through Autoregressive Prediction of Cochlear Tokens
Autoregressive prediction over discrete cochlear tokens yields a speech representation that beats prior self-supervised models on lexical-semantic similarity and is competitive on SUPERB tasks.