Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance

08/23/2019
by   Mahault Garnerin, et al.
0

This paper analyzes the gender representation in four major corpora of French broadcast. These corpora being widely used within the speech processing community, they are a primary material for training automatic speech recognition (ASR) systems. As gender bias has been highlighted in numerous natural language processing (NLP) applications, we study the impact of the gender imbalance in TV and radio broadcast on the performance of an ASR system. This analysis shows that women are under-represented in our data in terms of speakers and speech turns. We introduce the notion of speaker role to refine our analysis and find that women are even fewer within the Anchor category corresponding to prominent speakers. The disparity of available data for both gender causes performance to decrease on women. However this global trend can be counterbalanced for speaker who are used to speak in the media when sufficient amount of data is available.

READ FULL TEXT
research
09/09/2022

Overlapped speech and gender detection with WavLM pre-trained features

This article focuses on overlapped speech and gender detection in order ...
research
03/28/2021

Quantifying Bias in Automatic Speech Recognition

Automatic speech recognition (ASR) systems promise to deliver objective ...
research
07/20/2023

A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos

Automatic speech recognition (ASR) systems are designed to transcribe sp...
research
12/21/2015

The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media

We describe the University of Sheffield system for participation in the ...
research
12/09/2020

Breeding Gender-aware Direct Speech Translation Systems

In automatic speech translation (ST), traditional cascade approaches inv...
research
01/31/2018

Comparing approaches for mitigating intergroup variability in personality recognition

Personality have been found to predict many life outcomes, and there hav...

Please sign up or login with your details

Forgot password? Click here to reset