Exploring Rnn-transducer For Chinese Speech Recognition

Abstract

End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system. RNN transducer (RNN-T) is one of the popular end-to-end methods. Previous studies have shown that RNN-T is difficult to train and a very complex training process is needed for a reasonable performance. In this paper, we explore RNN-T for a Chinese large vocabulary continuous speech recognition (LVCSR) task and aim to simplify the training process while maintaining performance. First, a new strategy of learning rate decay is proposed to accelerate the model convergence. Second, we find that adding convolutional layers at the beginning of the network and using ordered data can discard the pre-training process of the encoder without loss of performance. Besides, we design experiments to find a balance among the usage of GPU memory, training circle and model performance. Finally, we achieve 16.9% character error rate (CER) on our test set

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keywang2018exploring

Related papers

• Improving RNN Transducer Modeling For End-to-end Speech Recognition (2019)0.00
• Cascade Rnn-transducer: Syllable Based Streaming On-device Mandarin Speech Recognition With A Syllable-to-character Converter (2020)9.92
• Exploring Architectures, Data And Units For Streaming End-to-end Speech Recognition With Rnn-transducer (2018)16.21
• Research On Modeling Units Of Transformer Transducer For Mandarin Speech Recognition (2020)0.00
• Self-attention Transducers For End-to-end Speech Recognition (2019)11.93
• Exploring Pre-training With Alignments For RNN Transducer Based End-to-end Speech Recognition (2020)9.41
• Multitask Learning And Joint Optimization For Transformer-rnn-transducer Speech Recognition (2020)8.09
• Minimum Bayes Risk Training Of Rnn-transducer For End-to-end Speech Recognition (2019)0.00