The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods

Abstract

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.

arXiv commentAccepted by ICASSP 2021

References in corpus (6)

• Attentive Statistics Pooling for Deep Speaker Embedding
• Conformer: Convolution-augmented Transformer for Speech Recognition
• A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition
• Domain Adversarial Training for Accented Speech Recognition
• Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification
• Multi-Accent Adaptation based on Gate Mechanism

Cited by in corpus (6)

• AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challenge
• Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning
• E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition
• Deep Discriminative Feature Learning for Accent Recognition
• Multilingual Approach to Joint Speech and Accent Recognition with DNN-HMM Framework
• Accent Recognition with Hybrid Phonetic Features