Saved in:
Bibliographic Details
Main Authors: Sekkat, Chloé, Leroy, Fanny, Mdhaffar, Salima, Smith, Blake Perry, Estève, Yannick, Dureau, Joseph, Coucke, Alice
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.19342
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913369827573760
author Sekkat, Chloé
Leroy, Fanny
Mdhaffar, Salima
Smith, Blake Perry
Estève, Yannick
Dureau, Joseph
Coucke, Alice
author_facet Sekkat, Chloé
Leroy, Fanny
Mdhaffar, Salima
Smith, Blake Perry
Estève, Yannick
Dureau, Joseph
Coucke, Alice
contents Recent works demonstrate that voice assistants do not perform equally well for everyone, but research on demographic robustness of speech technologies is still scarce. This is mainly due to the rarity of large datasets with controlled demographic tags. This paper introduces the Sonos Voice Control Bias Assessment Dataset, an open dataset composed of voice assistant requests for North American English in the music domain (1,038 speakers, 166 hours, 170k audio samples, with 9,040 unique labelled transcripts) with a controlled demographic diversity (gender, age, dialectal region and ethnicity). We also release a statistical demographic bias assessment methodology, at the univariate and multivariate levels, tailored to this specific use case and leveraging spoken language understanding metrics rather than transcription accuracy, which we believe is a better proxy for user experience. To demonstrate the capabilities of this dataset and statistical method to detect demographic bias, we consider a pair of state-of-the-art Automatic Speech Recognition and Spoken Language Understanding models. Results show statistically significant differences in performance across age, dialectal region and ethnicity. Multivariate tests are crucial to shed light on mixed effects between dialectal region, gender and age.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19342
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sonos Voice Control Bias Assessment Dataset: A Methodology for Demographic Bias Assessment in Voice Assistants
Sekkat, Chloé
Leroy, Fanny
Mdhaffar, Salima
Smith, Blake Perry
Estève, Yannick
Dureau, Joseph
Coucke, Alice
Sound
Computation and Language
Machine Learning
Audio and Speech Processing
Recent works demonstrate that voice assistants do not perform equally well for everyone, but research on demographic robustness of speech technologies is still scarce. This is mainly due to the rarity of large datasets with controlled demographic tags. This paper introduces the Sonos Voice Control Bias Assessment Dataset, an open dataset composed of voice assistant requests for North American English in the music domain (1,038 speakers, 166 hours, 170k audio samples, with 9,040 unique labelled transcripts) with a controlled demographic diversity (gender, age, dialectal region and ethnicity). We also release a statistical demographic bias assessment methodology, at the univariate and multivariate levels, tailored to this specific use case and leveraging spoken language understanding metrics rather than transcription accuracy, which we believe is a better proxy for user experience. To demonstrate the capabilities of this dataset and statistical method to detect demographic bias, we consider a pair of state-of-the-art Automatic Speech Recognition and Spoken Language Understanding models. Results show statistically significant differences in performance across age, dialectal region and ethnicity. Multivariate tests are crucial to shed light on mixed effects between dialectal region, gender and age.
title Sonos Voice Control Bias Assessment Dataset: A Methodology for Demographic Bias Assessment in Voice Assistants
topic Sound
Computation and Language
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2405.19342