.png){kind=icon}
.png){kind=icon}
Return
Towards inclusive automatic speech recognition
.png){kind=icon}
OA
AI
DOI：10.1016/j.csl.2023.101567.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Practice and recent evidence show that state-of-the-art (SotA) automatic speech recognition (ASR) systems do not perform equally well for all speaker groups. Many factors can cause this bias against different speaker groups. This paper, for the first time, systematically quantifies and finds speech recognition bias against gender, age, regional accents and non-native accents, and investigates the origin of this bias by investigating bias cross-lingually (i.e., Dutch and Mandarin) and for two different SotA ASR architectures (a hybrid DNN-HMM and an attention based end-to-end (E2E) model) through a phoneme error analysis. The results show that only a fraction of the bias can be explained by pronunciation differences between speaker groups, and that in order to mitigate bias, language- and architecture specific solutions need to be found.
Keywords:
Inclusive automatic speech recognition
Bias
Gender
Age
Accent
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
C
IF:
3.4
Papers:
1.5K
Citations:
2.6K