Pith. sign in

REVIEW

Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2008.02686 v1 pith:ZUB2JU5O submitted 2020-08-06 eess.AS cs.LGcs.MMcs.SD

classification eess.AScs.LGcs.MMcs.SD
keywords fusionaudio-visualencodingmethodmodalityproposedrecognitionattentive
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Audio-visual information fusion enables a performance improvement in speech recognition performed in complex acoustic scenarios, e.g., noisy environments. It is required to explore an effective audio-visual fusion strategy for audiovisual alignment and modality reliability. Different from the previous end-to-end approaches where the audio-visual fusion is performed after encoding each modality, in this paper we propose to integrate an attentive fusion block into the encoding process. It is shown that the proposed audio-visual fusion method in the encoder module can enrich audio-visual representations, as the relevance between the two modalities is leveraged. In line with the transformer-based architecture, we implement the embedded fusion block using a multi-head attention based audiovisual fusion with one-way or two-way interactions. The proposed method can sufficiently combine the two streams and weaken the over-reliance on the audio modality. Experiments on the LRS3-TED dataset demonstrate that the proposed method can increase the recognition rate by 0.55%, 4.51% and 4.61% on average under the clean, seen and unseen noise conditions, respectively, compared to the state-of-the-art approach.

Discussion (0). Continue with ORCID to comment.

Pith tools