Automatic Speech Recognition of African American English: Lexical and Contextual Effects

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mojarad, Hamid, Tang, Kevin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909750530146304
author Mojarad, Hamid
Tang, Kevin
author_facet Mojarad, Hamid
Tang, Kevin
contents Automatic Speech Recognition (ASR) models often struggle with the phonetic, phonological, and morphosyntactic features found in African American English (AAE). This study focuses on two key AAE variables: Consonant Cluster Reduction (CCR) and ING-reduction. It examines whether the presence of CCR and ING-reduction increases ASR misrecognition. Subsequently, it investigates whether end-to-end ASR systems without an external Language Model (LM) are more influenced by lexical neighborhood effect and less by contextual predictability compared to systems with an LM. The Corpus of Regional African American Language (CORAAL) was transcribed using wav2vec 2.0 with and without an LM. CCR and ING-reduction were detected using the Montreal Forced Aligner (MFA) with pronunciation expansion. The analysis reveals a small but significant effect of CCR and ING on Word Error Rate (WER) and indicates a stronger presence of lexical neighborhood effect in ASR systems without LMs.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06888
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatic Speech Recognition of African American English: Lexical and Contextual Effects
Mojarad, Hamid
Tang, Kevin
Computation and Language
Sound
Audio and Speech Processing
I.5; G.3
Automatic Speech Recognition (ASR) models often struggle with the phonetic, phonological, and morphosyntactic features found in African American English (AAE). This study focuses on two key AAE variables: Consonant Cluster Reduction (CCR) and ING-reduction. It examines whether the presence of CCR and ING-reduction increases ASR misrecognition. Subsequently, it investigates whether end-to-end ASR systems without an external Language Model (LM) are more influenced by lexical neighborhood effect and less by contextual predictability compared to systems with an LM. The Corpus of Regional African American Language (CORAAL) was transcribed using wav2vec 2.0 with and without an LM. CCR and ING-reduction were detected using the Montreal Forced Aligner (MFA) with pronunciation expansion. The analysis reveals a small but significant effect of CCR and ING on Word Error Rate (WER) and indicates a stronger presence of lexical neighborhood effect in ASR systems without LMs.
title Automatic Speech Recognition of African American English: Lexical and Contextual Effects
topic Computation and Language
Sound
Audio and Speech Processing
I.5; G.3
url https://arxiv.org/abs/2506.06888