 | This is the sandbox page where you will draft your initial Wikipedia contribution.
If you're starting a new article, you can develop it here until it's ready to go live. If you're working on improvements to an existing article, copy only one section at a time of the article to this sandbox to work on, and be sure to use an edit summary linking to the article you copied from. Do not copy over the entire article. You can find additional instructions here. Remember to save your work regularly using the "Publish page" button. (It just means 'save'; it will still be in the sandbox.) You can add bold formatting to your additions to differentiate them from existing content. |
Bias edit
Speech recognition tends to understand certain races and genders better than others. Speech recognition has a worse performance for women and non-white English speakers when looking at accuracy in English. [1]Speech recognition has difficulty with certain accents and dialects. The rate of accuracy depends on the dialect that is spoken. Scottish and Indian accents tended to be misunderstood by speech recognition programs, like YouTube's auto-captioning. [2]
These biases exist because speech recognition software has had more exposure to certain types of voices, which can lead to the programs getting voices not included in the training mistaken. Companies that use speech recognition are taking steps to try and fix the bias, but the bias exists on many speech recognition platforms today. [2]
- ^ Martin, Joshua; Wright, Kelly (2022-12-14). "Bias in Automatic Speech Recognition: The Case of African American Language". Applied Linguistics. 44 (4): 613–630 – via Oxford Academic.
- ^ a b Bajorek, Joan Palmiter (2019-05-10). "Voice Recognition Still Has Significant Race and Gender Biases". Harvard Business Review. ISSN 0017-8012. Retrieved 2023-10-13.