Improving RNN Transducer Based ASR With Auxiliary Tasks

Abstract

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer (RNN-T) has shown competitive ASR performance on various benchmarks. In this work, we examine ways in which RNN-T can achieve better ASR accuracy via performing auxiliary tasks. We propose (i) using the same auxiliary task as primary RNN-T ASR task, and (ii) performing context-dependent graphemic state prediction as in conventional hybrid modeling. In transcribing social media videos with varying training data size, we first evaluate the streaming ASR performance on three languages: Romanian, Turkish and German. We find that both proposed methods provide consistent improvements. Next, we observe that both auxiliary tasks demonstrate efficacy in learning deep transformer encoders for RNN-T criterion, thus achieving competitive results - 2.0%/4.2% WER on L

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keyliu2020improving

Related papers

• Improving RNN Transducer Modeling For End-to-end Speech Recognition (2019)0.00
• Improving RNN-T ASR Accuracy Using Context Audio (2020)5.84
• Integrating Text Inputs For Training And Adapting RNN Transducer ASR Models (2022)9.59
• Exploring Architectures, Data And Units For Streaming End-to-end Speech Recognition With Rnn-transducer (2018)16.21
• Improved Neural Language Model Fusion For Streaming Recurrent Neural Network Transducer (2020)8.82
• Multitask Learning And Joint Optimization For Transformer-rnn-transducer Speech Recognition (2020)8.09
• Alignment Restricted Streaming Recurrent Neural Network Transducer (2020)11.19
• Streaming Multi-speaker ASR With RNN-T (2020)10.07