Hybrid Attention-based Encoder-decoder Model For Efficient Language Model Adaptation

Abstract

The attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years. However, the joint optimization of acoustic model and language model in end-to-end manner has created challenges for text adaptation. In particular, effective, quick and inexpensive adaptation with text input has become a primary concern for deploying AED systems in the industry. To address this issue, we propose a novel model, the hybrid attention-based encoder-decoder (HAED) speech recognition model that preserves the modularity of conventional hybrid automatic speech recognition systems. Our HAED model separates the acoustic and language models, allowing for the use of conventional text-based language model adaptation techniques. We demonstrate that the proposed HAED model yields 23% relative Word Error Rate (WER) improvements when out-of-domain text data is used for language model adaptation, with only a minor degradation in WER on a general test set compared with the conv

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyling2023hybrid

Related papers

• Hybrid Transducer And Attention Based Encoder-decoder Modeling For Speech-to-text Tasks (2023)6.77
• Investigating Methods To Improve Language Model Integration For Attention-based Encoder-decoder ASR Models (2021)0.00
• Modular Hybrid Autoregressive Transducer (2022)8.35
• Optimizing Alignment Of Speech And Language Latent Spaces For End-to-end Speech Recognition And Understanding (2021)9.03
• Audio-attention Discriminative Language Model For ASR Rescoring (2019)9.23
• A Highly Adaptive Acoustic Model For Accurate Multi-dialect Speech Recognition (2022)10.85
• Audio Adversarial Examples For Robust Hybrid Ctc/attention Speech Recognition (2020)3.58
• Autoencoder Based Domain Adaptation For Speaker Recognition Under Insufficient Channel Information (2017)10.07