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.
Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling. The ideal neural audio codec should maintain content, paralinguistics, speaker characteristics, and audio information even at low bitrates. Recently, numerous advanced neural codec models have been proposed. However, codec models are often tested under varying experimental conditions. As a result, we introduce the Codec-SUPERB challenge at SLT 2024, designed to facilitate fair and lightweight comparisons among existing codec models and inspire advancements in the field. This challenge brings together representative speech applications and objective metrics, and carefully selects license-free datasets, sampling them into small sets to reduce evaluation computation costs. This paper presents the challenge's rules, datasets, five participant systems, results, and findings.
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.