Improving Code-switching And Named Entity Recognition In ASR With Speech Editing Based Data Augmentation

Abstract

Recently, end-to-end (E2E) automatic speech recognition (ASR) models have made great strides and exhibit excellent performance in general speech recognition. However, there remain several challenging scenarios that E2E models are not competent in, such as code-switching and named entity recognition (NER). Data augmentation is a common and effective practice for these two scenarios. However, the current data augmentation methods mainly rely on audio splicing and text-to-speech (TTS) models, which might result in discontinuous, unrealistic, and less diversified speech. To mitigate these potential issues, we propose a novel data augmentation method by applying the text-based speech editing model. The augmented speech from speech editing systems is more coherent and diversified, also more akin to real speech. The experimental results on code-switching and NER tasks show that our proposed method can significantly outperform the audio splicing and neural TTS based data augmentation systems.

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keyliang2023improving

Related papers

• Data Augmentation For End-to-end Code-switching Speech Recognition (2020)9.92
• Improving Low Resource Code-switched ASR Using Augmented Code-switched TTS (2020)7.50
• You Do Not Need More Data: Improving End-to-end Speech Recognition By Text-to-speech Data Augmentation (2020)11.49
• Improving Sequence-to-sequence Speech Recognition Training With On-the-fly Data Augmentation (2019)0.00
• Data Augmentation Methods For End-to-end Speech Recognition On Distant-talk Scenarios (2021)6.34
• Back-translation-style Data Augmentation For End-to-end ASR (2018)13.11
• Mixspeech: Data Augmentation For Low-resource Automatic Speech Recognition (2021)13.60
• Hmm-based Data Augmentation For E2E Systems For Building Conversational Speech Synthesis Systems (2022)0.00