On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode

TL;DR

This paper evaluates various attention-based end-to-end speech recognition models, focusing on their performance and latency in standalone and re-scoring modes, highlighting Transformer models as a promising approach for low-latency applications.

Contribution

It compares LSTM, Transformer, and Conformer encoders for streaming and re-scoring ASR, demonstrating Transformer’s efficiency and the impact of CNN front-ends on performance.

Findings

Transformer offers acceptable WER with low latency.

Second pass LAS re-scoring improves WER by around 16%.

CNN front-end enhances Transformer performance.

Abstract

The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits of the non-streaming model in streaming applications like voice search, it is commonly used in second pass re-scoring mode. The candidate hypothesis generated using steaming models is re-scored using a non-streaming model. In this work, we evaluate the non-streaming attention-based end-to-end ASR models on the Flipkart voice search task in both standalone and re-scoring modes. These models are based on Listen-Attend-Spell (LAS) encoder-decoder architecture. We experiment with different encoder variations based on LSTM, Transformer, and Conformer. We compare the latency requirements of these models along with their performance. Overall we show that the Transformer model offers acceptable WER with the lowest latency requirements. We report a relative WER improvement of around 16% with the second pass LAS re-scoring with latency overhead under 5ms. We also highlight the importance of CNN front-end with Transformer architecture to achieve comparable word error rates (WER). Moreover, we observe that in the second pass re-scoring mode all the encoders provide similar benefits whereas the difference in performance is prominent in standalone text generation mode.