Summary of The Balancing Act: Unmasking and Alleviating Asr Biases in Portuguese, by Ajinkya Kulkarni et al.
The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese
by Ajinkya Kulkarni, Anna Tokareva, Rameez Qureshi, Miguel Couceiro
First submitted to arxiv on: 12 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study examines biases in automatic speech recognition (ASR) for casual conversation speech in the Portuguese language. Researchers investigate categories like gender, age, skin tone color, and geo-location using Whisper and Multilingual Massive Speech (MMS) systems. Traditional ASR metrics like Word Error Rate (WER) are combined with p-value statistical significance to analyze gender bias. The impact of data distribution is also explored, showing that oversampling techniques can alleviate stereotypical biases. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how well machines can understand spoken language in Portugal. It checks for biases towards certain groups, like men or women, and finds that these biases exist. The researchers use special systems called Whisper and MMS to analyze the speech. They want to know why these biases happen and if they can be fixed by changing how the data is used. |
