Synchronous Transformers For End-to-end Speech Recognition

Abstract

For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these models difficult to be applied for online speech recognition. In this paper, we propose a model named synchronous transformer to address this problem, which can predict the output sequence chunk by chunk. Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately. During training, a forward-backward algorithm is introduced to optimize all the possible alignment paths. Our model is evaluated on a Mandarin dataset AISHELL-1. The experiments show that the synchronous transformer is able to perform encoding and decoding synchronously, and achieves a character error rate of 8.91% on the test set.

Stats

• citations39
• S2 citations—
• github stars0
• HF likes0
• heat score12.02
• arxiv keytian2019synchronous

Related papers

• Spike-triggered Non-autoregressive Transformer For End-to-end Speech Recognition (2020)11.39
• Transformer-based Online Ctc/attention End-to-end Speech Recognition Architecture (2020)14.06
• Transformer-based Online Speech Recognition With Decoder-end Adaptive Computation Steps (2020)7.81
• Conv-transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-end Speech Recognition (2020)11.08
• A Comparison Of Label-synchronous And Frame-synchronous End-to-end Models For Speech Recognition (2020)0.00
• S-transformer: Segment-transformer For Robust Neural Speech Synthesis (2020)0.00
• Fast Offline Transformer-based End-to-end Automatic Speech Recognition For Real-world Applications (2021)7.16
• Self-attention Transducers For End-to-end Speech Recognition (2019)11.93