Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Onda, Kentaro, Imoto, Keisuke, Fukayama, Satoru, Saito, Daisuke, Minematsu, Nobuaki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915297851604992
author Onda, Kentaro
Imoto, Keisuke
Fukayama, Satoru
Saito, Daisuke
Minematsu, Nobuaki
author_facet Onda, Kentaro
Imoto, Keisuke
Fukayama, Satoru
Saito, Daisuke
Minematsu, Nobuaki
contents In this study, we gained insight that contributes to achieving accent-robust ASR using only native speech data. In human perception of non-native speech, the phenomenon known as "interlanguage speech intelligibility benefit" (ISIB) is observed, where non-native listeners who share the native language with the speaker understand the speech better compared even to native listeners. Based on the idea that discrete tokens extracted from self-supervised learning (SSL) models represent the human perception of speech, we conducted an analytical study on the robustness of discrete token-based ASR to non-native speech, varying the language used for training the tokenization, which is viewed as a technical implementation of ISIB. The results showed that ISIB actually occurred in the discrete token-based ASR. Since our approach relies only on native speech data to simulate the behavior of human perception, it is expected to be applicable to a wide range of accents for which speech data is scarce.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16182
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data
Onda, Kentaro
Imoto, Keisuke
Fukayama, Satoru
Saito, Daisuke
Minematsu, Nobuaki
Sound
Audio and Speech Processing
In this study, we gained insight that contributes to achieving accent-robust ASR using only native speech data. In human perception of non-native speech, the phenomenon known as "interlanguage speech intelligibility benefit" (ISIB) is observed, where non-native listeners who share the native language with the speaker understand the speech better compared even to native listeners. Based on the idea that discrete tokens extracted from self-supervised learning (SSL) models represent the human perception of speech, we conducted an analytical study on the robustness of discrete token-based ASR to non-native speech, varying the language used for training the tokenization, which is viewed as a technical implementation of ISIB. The results showed that ISIB actually occurred in the discrete token-based ASR. Since our approach relies only on native speech data to simulate the behavior of human perception, it is expected to be applicable to a wide range of accents for which speech data is scarce.
title Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.16182