On Minimum Word Error Rate Training Of The Hybrid Autoregressive Transducer

Abstract

Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end acoustic model that extends the standard Recurrent Neural Network Transducer (RNN-T) for the purpose of the external language model (LM) fusion. In HAT, the blank probability and the label probability are estimated using two separate probability distributions, which provides a more accurate solution for internal LM score estimation, and thus works better when combining with an external LM. Previous work mainly focuses on HAT model training with the negative log-likelihood loss, while in this paper, we study the minimum word error rate (MWER) training of HAT -- a criterion that is closer to the evaluation metric for speech recognition, and has been successfully applied to other types of end-to-end models such as sequence-to-sequence (S2S) and RNN-T models. From experiments with around 30,000 hours of training data, we show that MWER training can improve the accuracy of HAT models, while at the same time, improving

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keylu2020on

Related papers

• Modular Hybrid Autoregressive Transducer (2022)8.35
• Efficient Minimum Word Error Rate Training Of Rnn-transducer For End-to-end Speech Recognition (2020)11.19
• Boosting Hybrid Autoregressive Transducer-based ASR With Internal Acoustic Model Training And Dual Blank Thresholding (2024)2.26
• Minimum Word Error Rate Training For Attention-based Sequence-to-sequence Models (2017)14.35
• Minimum Bayes Risk Training Of Rnn-transducer For End-to-end Speech Recognition (2019)0.00
• Improving RNN Transducer Modeling For End-to-end Speech Recognition (2019)0.00
• H_eval: A New Hybrid Evaluation Metric For Automatic Speech Recognition Tasks (2022)6.34
• Multiple-hypothesis RNN-T Loss For Unsupervised Fine-tuning And Self-training Of Neural Transducer (2022)0.00