What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kloots, Marianne de Heer, Mohebbi, Hosein, Pouw, Charlotte, Shen, Gaofei, Zuidema, Willem, Bentum, Martijn
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913935545860096
author Kloots, Marianne de Heer
Mohebbi, Hosein
Pouw, Charlotte
Shen, Gaofei
Zuidema, Willem
Bentum, Martijn
author_facet Kloots, Marianne de Heer
Mohebbi, Hosein
Pouw, Charlotte
Shen, Gaofei
Zuidema, Willem
Bentum, Martijn
contents How language-specific are speech representations learned by self-supervised models? Existing work has shown that a range of linguistic features can be successfully decoded from end-to-end models trained only on speech recordings. However, it's less clear to what extent pre-training on specific languages improves language-specific linguistic information. Here we test the encoding of Dutch phonetic and lexical information in internal representations of self-supervised Wav2Vec2 models. Pre-training exclusively on Dutch improves the representation of Dutch linguistic features as compared to pre-training on similar amounts of English or larger amounts of multilingual data. This language-specific advantage is well-detected by trained clustering or classification probes, and partially observable using zero-shot metrics. Furthermore, the language-specific benefit on linguistic feature encoding aligns with downstream performance on Automatic Speech Recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training
Kloots, Marianne de Heer
Mohebbi, Hosein
Pouw, Charlotte
Shen, Gaofei
Zuidema, Willem
Bentum, Martijn
Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
How language-specific are speech representations learned by self-supervised models? Existing work has shown that a range of linguistic features can be successfully decoded from end-to-end models trained only on speech recordings. However, it's less clear to what extent pre-training on specific languages improves language-specific linguistic information. Here we test the encoding of Dutch phonetic and lexical information in internal representations of self-supervised Wav2Vec2 models. Pre-training exclusively on Dutch improves the representation of Dutch linguistic features as compared to pre-training on similar amounts of English or larger amounts of multilingual data. This language-specific advantage is well-detected by trained clustering or classification probes, and partially observable using zero-shot metrics. Furthermore, the language-specific benefit on linguistic feature encoding aligns with downstream performance on Automatic Speech Recognition.
title What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training
topic Computation and Language
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.00981