Do speech recognizers prefer female speakers?

By Martine Adda-Decker, Lori Faith Lamel. 2005

84 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Language and Linguistics, Speech & Audio, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dan Jurafsky
2. James R. Glass
3. Christopher D. Manning
4. Percy Liang
5. Noah A. Smith
6. Mohit Bansal
7. Luke S. Zettlemoyer
8. Yonatan Belinkov

In Experimental and Cognitive Psychology

1. Christopher D. Manning
2. Dan Jurafsky
3. Sharon Goldwater
4. J. Rickford
5. Rachael Tatman

In Language and Linguistics

1. Christopher D. Manning
2. Dan Jurafsky
3. Sharon Goldwater
4. J. Rickford
5. Jillian Grennan

In Speech & Audio

1. Christopher D. Manning
2. Dan Jurafsky
3. Sharon Goldwater
4. James R. Glass
5. Rachael Tatman
6. Herman Kamper
7. David F. Harwath
8. Karen Livescu

In AI Ethics, Fairness & Society

1. Sharad Goel
2. Dan Jurafsky

Citations in the corpus

• Racial disparities in automated speech recognition (2020, background): “This restriction allowed us to focus on racial disparities, as age and gender are also known to impact the performance of ASR systems (28, 29).”
• Which words are hard to recognize? Prosodic, lexical, and disfluency factors that increase speech recognition error rates (2010, background): “The remaining small differences may be accounted for by males’ increased use of alternate pronunciations, as suggested by Adda-Decker and Lamel (2005).”