An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR

TL;DR

This paper proposes a novel streaming ASR system combining Mask-CTC and triggered attention, achieving high accuracy with low latency by leveraging future context learning during encoder pre-training.

Contribution

It introduces the integration of Mask-CTC with triggered attention for improved streaming ASR performance and low latency.

Findings

Higher accuracy than conventional systems.

Lower latency achieved in experiments.

Effective use of future context learning.

Abstract

In the present paper, an attempt is made to combine Mask-CTC and the triggered attention mechanism to construct a streaming end-to-end automatic speech recognition (ASR) system that provides high performance with low latency. The triggered attention mechanism, which performs autoregressive decoding triggered by the CTC spike, has shown to be effective in streaming ASR. However, in order to maintain high accuracy of alignment estimation based on CTC outputs, which is the key to its performance, it is inevitable that decoding should be performed with some future information input (i.e., with higher latency). It should be noted that in streaming ASR, it is desirable to be able to achieve high recognition accuracy while keeping the latency low. Therefore, the present study aims to achieve highly accurate streaming ASR with low latency by introducing Mask-CTC, which is capable of learning feature representations that anticipate future information (i.e., that can consider long-term contexts), to the encoder pre-training. Experimental comparisons conducted using WSJ data demonstrate that the proposed method achieves higher accuracy with lower latency than the conventional triggered attention-based streaming ASR system.