The Zero Resource Speech Challenge 2021: Spoken language modelling - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

The Zero Resource Speech Challenge 2021: Spoken language modelling

Abstract

We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels. The challenge is based on the Libri-light dataset, which provides up to 60k hours of audio from English audio books without any associated text. We provide a pipeline baseline system consisting on an encoder based on contrastive predictive coding (CPC), a quantizer ($k$-means) and a standard language model (BERT or LSTM). The metrics evaluate the learned representations at the acoustic (ABX discrimination), lexical (spot-the-word), syntactic (acceptability judgment) and semantic levels (similarity judgment). We present an overview of the eight submitted systems from four groups and discuss the main results.
Fichier principal
Vignette du fichier
2104.14700 (1).pdf (129.19 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03329301 , version 1 (30-08-2021)
hal-03329301 , version 2 (11-10-2021)

Identifiers

Cite

Ewan Dunbar, Mathieu Bernard, Nicolas Hamilakis, Tu Anh Nguyen, Maureen de Seyssel, et al.. The Zero Resource Speech Challenge 2021: Spoken language modelling. Interspeech 2021 - Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. ⟨10.1109/TPAMI.2021.3083839⟩. ⟨hal-03329301v2⟩
127 View
170 Download

Altmetric

Share

Gmail Facebook X LinkedIn More