학술논문
Cross-Attention Conformer for Context Modeling in Speech Enhancement for ASR
Document Type
Conference
Source
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Automatic Speech Recognition and Understanding Workshop (ASRU), 2021 IEEE. :312-319 Dec, 2021
Subject
Language
Abstract
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.