Spike-triggered Non-autoregressive Transformer For End-to-end Speech Recognition

Abstract

Non-autoregressive transformer models have achieved extremely fast inference speed and comparable performance with autoregressive sequence-to-sequence models in neural machine translation. Most of the non-autoregressive transformers decode the target sequence from a predefined-length mask sequence. If the predefined length is too long, it will cause a lot of redundant calculations. If the predefined length is shorter than the length of the target sequence, it will hurt the performance of the model. To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence. All the experiments are conducted on a public Chinese mandarin dataset AISHELL-1. The results show that the proposed model can accurately predict the length of the target sequence and achieve a competitive performance with the adva

Stats

• citations32
• S2 citations—
• github stars0
• HF likes0
• heat score11.39
• arxiv keytian2020spike

Related papers

• Synchronous Transformers For End-to-end Speech Recognition (2019)12.02
• A CTC Alignment-based Non-autoregressive Transformer For End-to-end Automatic Speech Recognition (2023)10.97
• Transformer-based Online Ctc/attention End-to-end Speech Recognition Architecture (2020)14.06
• Non-autoregressive Transformer ASR With Ctc-enhanced Decoder Input (2020)10.97
• Fast Offline Transformer-based End-to-end Automatic Speech Recognition For Real-world Applications (2021)7.16
• Automatic Spelling Correction With Transformer For Ctc-based End-to-end Speech Recognition (2019)0.00
• Self-attention Transducers For End-to-end Speech Recognition (2019)11.93
• One In A Hundred: Select The Best Predicted Sequence From Numerous Candidates For Streaming Speech Recognition (2020)0.00