Multi-Head Decoder for End-to-End Speech Recognition

TL;DR

This paper introduces a multi-head decoder architecture for end-to-end speech recognition, using multiple decoders and diverse attention functions to improve recognition accuracy by capturing different speech contexts.

Contribution

The proposed multi-head decoder extends multi-head attention by employing separate decoders with different attention functions, enhancing speech recognition performance through diverse context modeling.

Findings

Outperforms conventional attention models on Japanese speech data

Captures diverse speech and linguistic contexts effectively

Demonstrates improved recognition accuracy

Abstract

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then, they are integrated into a single attention. On the other hand, instead of the integration in the attention level, our proposed method uses multiple decoders for each attention and integrates their outputs to generate a final output. Furthermore, in order to make each head to capture the different modalities, different attention functions are used for each head, leading to the improvement of the recognition performance with an ensemble effect. To evaluate the effectiveness of our proposed method, we conduct an experimental evaluation using Corpus of Spontaneous Japanese. Experimental results demonstrate that our proposed method outperforms the conventional methods such as location-based and multi-head attention models, and that it can capture different speech/linguistic contexts within the attention-based encoder-decoder framework.