# Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder

arXiv: https://arxiv.org/abs/2207.04177 · HTML: https://mlsanity.com/paper/2207.04177/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2022.

## Built on by (most cited first, 3 of 3)

- [Improving Massively Multilingual ASR With Auxiliary CTC Objectives](https://mlsanity.com/paper/2302.12829/) (2023)
- [Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding](https://mlsanity.com/paper/2412.16507/) (2024)
- [Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network](https://mlsanity.com/paper/2309.08489/) (2023)

## Abstract (arXiv)

Intermediate layer output (ILO) regularization by means of multitask training on encoder side has been shown to be an effective approach to yielding improved results on a wide range of end-to-end ASR frameworks. In this paper, we propose a novel method to do ILO regularized training differently. Instead of using conventional multitask methods that entail more training overhead, we directly make the intermediate layer output as input to the decoder, that is, our decoder not only accepts the output of the final encoder layer as input, it also takes the output of the encoder ILO as input during training. With the proposed method, as both encoder and decoder are simultaneously "regularized", the network is more sufficiently trained, consistently leading to improved results, over the ILO-based CTC method, as well as over the original attention-based modeling method without the proposed method employed.