ASR Benchmarking: Need for a More Representative Conversational Dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maheshwari, Gaurav, Ivanov, Dmitry, Johannet, Théo, Haddad, Kevin El
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913506423472128
author Maheshwari, Gaurav
Ivanov, Dmitry
Johannet, Théo
Haddad, Kevin El
author_facet Maheshwari, Gaurav
Ivanov, Dmitry
Johannet, Théo
Haddad, Kevin El
contents Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational environments, where speech is often unstructured and contains disfluencies such as pauses, interruptions, and diverse accents. In this study, we introduce a multilingual conversational dataset, derived from TalkBank, consisting of unstructured phone conversation between adults. Our results show a significant performance drop across various state-of-the-art ASR models when tested in conversational settings. Furthermore, we observe a correlation between Word Error Rate and the presence of speech disfluencies, highlighting the critical need for more realistic, conversational ASR benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12042
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ASR Benchmarking: Need for a More Representative Conversational Dataset
Maheshwari, Gaurav
Ivanov, Dmitry
Johannet, Théo
Haddad, Kevin El
Computation and Language
Sound
Audio and Speech Processing
Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational environments, where speech is often unstructured and contains disfluencies such as pauses, interruptions, and diverse accents. In this study, we introduce a multilingual conversational dataset, derived from TalkBank, consisting of unstructured phone conversation between adults. Our results show a significant performance drop across various state-of-the-art ASR models when tested in conversational settings. Furthermore, we observe a correlation between Word Error Rate and the presence of speech disfluencies, highlighting the critical need for more realistic, conversational ASR benchmarks.
title ASR Benchmarking: Need for a More Representative Conversational Dataset
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.12042