Effects of Talker Dialect, Gender & Race on Accuracy of Bing Speech and YouTube Automatic Captions

@inproceedings{Tatman2017EffectsOT,
  title={Effects of Talker Dialect, Gender & Race on Accuracy of Bing Speech and YouTube Automatic Captions},
  author={Rachael Tatman and C. Kasten},
  booktitle={INTERSPEECH},
  year={2017}
}
This project compares the accuracy of two automatic speech recognition (ASR) systems–Bing Speech and YouTube’s automatic captions–across gender, race and four dialects of American English. The dialects included were chosen for their acoustic dissimilarity. Bing Speech had differences in word error rate (WER) between dialects and ethnicities, but they were not statistically reliable. YouTube’s automatic captions, however, did have statistically different WERs between dialects and races. The… Expand
12 Citations
Understanding Racial Disparities in Automatic Speech Recognition: The Case of Habitual "be"
  • PDF
Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance
  • 7
  • Highly Influenced
  • PDF
Eschewing Gender Stereotypes in Voice Assistants to Promote Inclusion
  • 1
  • PDF
Quantifying Bias in Automatic Speech Recognition
  • PDF
Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications
  • Highly Influenced
  • PDF
Racial disparities in automated speech recognition
  • 24
  • PDF
Adversarial Learning of Raw Speech Features for Domain Invariant Speech Recognition
  • 14
  • PDF
Improving MOOC quality using learning analytics and tools
  • 1
Pratiques d'évaluation en ASR et biais de performance (Evaluation methodology in ASR and performance bias)
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 24 REFERENCES
Gender and Dialect Bias in YouTube's Automatic Captions
  • 94
  • PDF
Pronunciation modeling for dialectal arabic speech recognition
  • 17
  • PDF
Discriminative pronunciation modeling for dialectal speech recognition
  • 12
  • PDF
Automatic speech recognition and speech variability: A review
  • 395
  • PDF
Unsupervised model selection for recognition of regional accented speech
  • 28
  • PDF
African American Vernacular English: Features, Evolution, Educational Implications
  • 263
Is word error rate a good indicator for spoken language understanding accuracy
  • 125
  • PDF
...
1
2
3
...