# Efficient infusion of self-supervised representations in Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2404.12628 · HTML: https://mlsanity.com/paper/2404.12628/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 19 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [LEAF: A Learnable Frontend for Audio Classification](https://mlsanity.com/paper/2101.08596/) (2021)
- [Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition](https://mlsanity.com/paper/2109.01163/) (2021)
- [Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings](https://mlsanity.com/paper/2110.03520/) (2021)
- [Multi-level Fusion of Wav2vec 2.0 and BERT for Multimodal Emotion Recognition](https://mlsanity.com/paper/2207.04697/) (2022)

## Abstract (arXiv)

Self-supervised learned (SSL) models such as Wav2vec and HuBERT yield state-of-the-art results on speech-related tasks. Given the effectiveness of such models, it is advantageous to use them in conventional ASR systems. While some approaches suggest incorporating these models as a trainable encoder or a learnable frontend, training such systems is extremely slow and requires a lot of computation cycles. In this work, we propose two simple approaches that use (1) framewise addition and (2) cross-attention mechanisms to efficiently incorporate the representations from the SSL model(s) into the ASR architecture, resulting in models that are comparable in size with standard encoder-decoder conformer systems while also avoiding the usage of SSL models during training. Our approach results in faster training and yields significant performance gains on the Librispeech and Tedlium datasets compared to baselines. We further provide detailed analysis and ablation studies that demonstrate the effectiveness of our approach.