Transformer-Transducer: End-to-End Speech Recognition with Self-Attention

Abstract

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts. We propose 1) using VGGNet with causal convolution to incorporate positional information and reduce frame rate for efficient inference 2) using truncated self-attention to enable streaming for Transformer and reduce computational complexity. All experiments are conducted on the public LibriSpeech corpus. The proposed Transformer-Transducer outperforms neural transducer with LSTM/BLSTM networks and achieved word error rates of 6.37 % on the test-clean set and 15.30 % on the test-other set, while remaining streamable, compact with 45.7M parameters for the entire system, and computationally efficient with complexity of O(T), where T is input sequence length.

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence Transduction with Recurrent Neural Networks

Cited by in corpus (6)

• A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition
• Attention-based Transducer for Online Speech Recognition
• Weak-Attention Suppression For Transformer Based Speech Recognition
• Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition
• Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition
• Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory