Domain Adversarial Training For Accented Speech Recognition

Abstract

In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data ("standard" accent) and unlabeled target domain data (with heavy accents), we augment the learning objective for a Kaldi TDNN network with a domain adversarial training (DAT) objective to encourage the model to learn accent-invariant features. In experiments with three Mandarin accents, we show that DAT yields up to 7.45% relative character error rate reduction when we do not have transcriptions of the accented speech, compared with the baseline trained on standard accent data only. We also find a benefit from DAT when used in combination with training from automatic transcriptions on the accented data. Furthermore, we find that DAT is superior to multi-task learning for accented speech recognition.

Stats

• citations69
• S2 citations—
• github stars0
• HF likes0
• heat score13.84
• arxiv keysun2018domain

Related papers

• Domain Adversarial Neural Networks For Dysarthric Speech Recognition (2020)7.50
• Attentive Adversarial Learning For Domain-invariant Training (2019)6.77
• Accent-robust Automatic Speech Recognition Using Supervised And Unsupervised Wav2vec Embeddings (2021)0.00
• Adversarial Training For Multi-domain Speaker Recognition (2020)6.77
• Adversarial Learning Of Raw Speech Features For Domain Invariant Speech Recognition (2018)9.23
• Best Of Both Worlds: Robust Accented Speech Recognition With Adversarial Transfer Learning (2021)9.23
• Cross-lingual Text-independent Speaker Verification Using Unsupervised Adversarial Discriminative Domain Adaptation (2019)11.85
• MADI: Inter-domain Matching And Intra-domain Discrimination For Cross-domain Speech Recognition (2023)7.50