Everyone deserves their voice to be heard: Analyzing Predictive Gender Bias in ASR Models Applied to Dutch Speech Data

• URL: http://arxiv.org/abs/2411.09431v1
• Date: Thu, 14 Nov 2024 13:29:09 GMT
• Title: Everyone deserves their voice to be heard: Analyzing Predictive Gender Bias in ASR Models Applied to Dutch Speech Data
• Authors: Rik Raes, Saskia Lensink, Mykola Pechenizkiy,
• Abstract summary: This study focuses on identifying the performance disparities of Whisper models on Dutch speech data. We analyzed the word error rate, character error rate and a BERT-based semantic similarity across gender groups.
• Score: 13.91630413828167
• License:
• Abstract: Recent research has shown that state-of-the-art (SotA) Automatic Speech Recognition (ASR) systems, such as Whisper, often exhibit predictive biases that disproportionately affect various demographic groups. This study focuses on identifying the performance disparities of Whisper models on Dutch speech data from the Common Voice dataset and the Dutch National Public Broadcasting organisation. We analyzed the word error rate, character error rate and a BERT-based semantic similarity across gender groups. We used the moral framework of Weerts et al. (2022) to assess quality of service harms and fairness, and to provide a nuanced discussion on the implications of these biases, particularly for automatic subtitling. Our findings reveal substantial disparities in word error rate (WER) among gender groups across all model sizes, with bias identified through statistical testing.

Related papers

• DENOASR: Debiasing ASRs through Selective Denoising [5.544079217915537]
  We introduce a novel framework DENOASR, which is a selective denoising technique to reduce the disparity in the word error rates between the two gender groups. We find that a combination of two popular speech denoising techniques, viz. DEMUCS and LE, can be effectively used to mitigate ASR disparity without compromising their overall performance.
  arXiv  Detail & Related papers  (2024-10-22T05:39:24Z)
• Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models [50.40276881893513]
  This study introduces Spoken Stereoset, a dataset specifically designed to evaluate social biases in Speech Large Language Models (SLLMs) By examining how different models respond to speech from diverse demographic groups, we aim to identify these biases. The findings indicate that while most models show minimal bias, some still exhibit slightly stereotypical or anti-stereotypical tendencies.
  arXiv  Detail & Related papers  (2024-08-14T16:55:06Z)
• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing [72.0343083866144]
  This paper introduces the GenderBias-emphVL benchmark to evaluate occupation-related gender bias in Large Vision-Language Models. Using our benchmark, we extensively evaluate 15 commonly used open-source LVLMs and state-of-the-art commercial APIs. Our findings reveal widespread gender biases in existing LVLMs.
  arXiv  Detail & Related papers  (2024-06-30T05:55:15Z)
• Sonos Voice Control Bias Assessment Dataset: A Methodology for Demographic Bias Assessment in Voice Assistants [10.227469020901232]
  This paper introduces the Sonos Voice Control Bias Assessment dataset. 1,038 speakers, 166 hours, 170k audio samples, with 9,040 unique labelled transcripts. Results show statistically significant differences in performance across age, dialectal region and ethnicity.
  arXiv  Detail & Related papers  (2024-05-14T12:53:32Z)
• The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese [5.308321515594125]
  This study is dedicated to a comprehensive exploration of the Whisper and MMS systems. Our investigation encompasses various categories, including gender, age, skin tone color, and geo-location. We empirically show that oversampling techniques alleviate such stereotypical biases.
  arXiv  Detail & Related papers  (2024-02-12T09:35:13Z)
• No Pitch Left Behind: Addressing Gender Unbalance in Automatic Speech Recognition through Pitch Manipulation [20.731375136671605]
  We propose a data augmentation technique that manipulates the fundamental frequency (f0) and formants. This technique reduces the data unbalance among genders by simulating voices of the under-represented female speakers. Experiments on spontaneous English speech show that our technique yields a relative WER improvement up to 9.87% for utterances by female speakers.
  arXiv  Detail & Related papers  (2023-10-10T12:55:22Z)
• Elucidate Gender Fairness in Singing Voice Transcription [5.434559527051845]
  We investigate whether gender-based characteristics lead to a performance disparity in singing voice transcription (SVT) We find that different pitch distributions, rather than gender data imbalance, contribute to this disparity. To address this issue, we propose using an attribute predictor to predict gender labels and adversarially training the SVT system to enforce the gender-invariance of acoustic representations.
  arXiv  Detail & Related papers  (2023-08-05T15:15:01Z)
• Social Biases in Automatic Evaluation Metrics for NLG [53.76118154594404]
  We propose an evaluation method based on Word Embeddings Association Test (WEAT) and Sentence Embeddings Association Test (SEAT) to quantify social biases in evaluation metrics. We construct gender-swapped meta-evaluation datasets to explore the potential impact of gender bias in image caption and text summarization tasks.
  arXiv  Detail & Related papers  (2022-10-17T08:55:26Z)
• Balancing Biases and Preserving Privacy on Balanced Faces in the Wild [50.915684171879036]
  There are demographic biases present in current facial recognition (FR) models. We introduce our Balanced Faces in the Wild dataset to measure these biases across different ethnic and gender subgroups. We find that relying on a single score threshold to differentiate between genuine and imposters sample pairs leads to suboptimal results. We propose a novel domain adaptation learning scheme that uses facial features extracted from state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2021-03-16T15:05:49Z)
• Gender Stereotype Reinforcement: Measuring the Gender Bias Conveyed by Ranking Algorithms [68.85295025020942]
  We propose the Gender Stereotype Reinforcement (GSR) measure, which quantifies the tendency of a Search Engines to support gender stereotypes. GSR is the first specifically tailored measure for Information Retrieval, capable of quantifying representational harms.
  arXiv  Detail & Related papers  (2020-09-02T20:45:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.