# Cross-attention conformer for context modeling in speech enhancement for ASR

arXiv: https://arxiv.org/abs/2111.00127 · HTML: https://mlsanity.com/paper/2111.00127/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2021.

## Built on by (most cited first, 2 of 2)

- [Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech](https://mlsanity.com/paper/2202.12163/) (2022)
- [Closing the Gap between Single-User and Multi-User VoiceFilter-Lite](https://mlsanity.com/paper/2202.12169/) (2022)

## Abstract (arXiv)

This work introduces cross-attention conformer, an attention-based architecture for context modeling in speech enhancement. Given that the context information can often be sequential, and of different length as the audio that is to be enhanced, we make use of cross-attention to summarize and merge contextual information with input features. Building upon the recently proposed conformer model that uses self attention layers as building blocks, the proposed cross-attention conformer can be used to build deep contextual models. As a concrete example, we show how noise context, i.e., short noise-only audio segment preceding an utterance, can be used to build a speech enhancement feature frontend using cross-attention conformer layers for improving noise robustness of automatic speech recognition.