Parallel Rescoring With Transformer For Streaming On-device Speech Recognition

Abstract

Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-device speech recognition, where a 1st-pass model generates hypotheses in a streaming fashion, and a 2nd-pass model re-scores the hypotheses with full audio sequence context. The 2nd-pass model plays a key role in the quality improvement of the end-to-end model to surpass the conventional model. One main challenge of the two-pass model is the computation latency introduced by the 2nd-pass model. Specifically, the original design of the two-pass model uses LSTMs for the 2nd-pass model, which are subject to long latency as they are constrained by the recurrent nature and have to run inference sequentially. In this work we explore replacing the LSTM layers in the 2nd-pass rescorer with Transformer layers, which can process the entire hypothesis sequences in parallel and can therefore utilize the on-device computat

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keyli2020parallel

Related papers

• Conv-transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-end Speech Recognition (2020)11.08
• Developing Real-time Streaming Transformer Transducer For Speech Recognition On Large-scale Dataset (2020)0.00
• On Comparison Of Encoders For Attention Based End To End Speech Recognition In Standalone And Rescoring Mode (2022)2.26
• Transformer Transducer: One Model Unifying Streaming And Non-streaming Speech Recognition (2020)0.00
• Streaming Parrotron For On-device Speech-to-speech Conversion (2022)2.26
• Transformer Transducer: A Streamable Speech Recognition Model With Transformer Encoders And RNN-T Loss (2020)18.58
• Two-pass End-to-end Speech Recognition (2019)13.97
• A Streaming On-device End-to-end Model Surpassing Server-side Conventional Model Quality And Latency (2020)15.00