Audio-attention Discriminative Language Model For ASR Rescoring

Abstract

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these models typically require more data to achieve comparable results. Well-known model adaptation techniques, to account for domain and style adaptation, are not easily applicable to end-to-end systems. Conventional HMM-based systems, on the other hand, have been optimized for various production environments and use cases. In this work, we propose to combine the benefits of end-to-end approaches with a conventional system using an attention-based discriminative language model that learns to rescore the output of a first-pass ASR system. We show that learning to rescore a list of potential ASR outputs is much simpler than learning to generate the hypothesis. The proposed model results in 8% improvement in word error rate even when the amount of training da

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keygandhe2019audio

Related papers

• Discriminative Speech Recognition Rescoring With Pre-trained Language Models (2023)2.26
• Multi-task Language Modeling For Improving Speech Recognition Of Rare Words (2020)8.35
• A Spelling Correction Model For End-to-end Speech Recognition (2019)14.62
• State-of-the-art Speech Recognition With Sequence-to-sequence Models (2017)21.01
• Integrating Source-channel And Attention-based Sequence-to-sequence Models For Speech Recognition (2019)8.09
• Independent Language Modeling Architecture For End-to-end ASR (2019)0.00
• An Online Attention-based Model For Speech Recognition (2018)9.59
• A Comparison Of End-to-end Models For Long-form Speech Recognition (2019)12.93