The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods
This provides a standardized dataset and benchmark for researchers working on accent-related speech recognition, though it is incremental as it builds on existing challenge frameworks.
The paper introduced the Accented English Speech Recognition Challenge 2020, which tackled the problem of accent diversity in speech recognition by releasing 160 hours of labeled accented English speech from 8 countries and 20 hours of unlabeled test data, including unseen accents, to benchmark model performance.
The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge -- English accent recognition (track 1) and accented English speech recognition (track 2). A set of 160 hours of accented English speech collected from 8 countries is released with labels as the training set. Another 20 hours of speech without labels is later released as the test set, including two unseen accents from another two countries used to test the model generalization ability in track 2. We also provide baseline systems for the participants. This paper first reviews the released dataset, track setups, baselines and then summarizes the challenge results and major techniques used in the submissions.