Pith. sign in

REVIEW 1 cited by

Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer

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 2410.04159 v1 pith:AVMK5JFD submitted 2024-10-05 cs.SD eess.AS

classification cs.SDeess.AS
keywords long-formmhsarecognitionspeechefficientlayerscomputationh3-conformer
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recently, Conformer has achieved state-of-the-art performance in many speech recognition tasks. However, the Transformer-based models show significant deterioration for long-form speech, such as lectures, because the self-attention mechanism becomes unreliable with the computation of the square order of the input length. To solve the problem, we incorporate a kind of state-space model, Hungry Hungry Hippos (H3), to replace or complement the multi-head self-attention (MHSA). H3 allows for efficient modeling of long-form sequences with a linear-order computation. In experiments using two datasets of CSJ and LibriSpeech, our proposed H3-Conformer model performs efficient and robust recognition of long-form speech. Moreover, we propose a hybrid of H3 and MHSA and show that using H3 in higher layers and MHSA in lower layers provides significant improvement in online recognition. We also investigate a parallel use of H3 and MHSA in all layers, resulting in the best performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Bidirectional recurrent attention with Direction Dropout matches or exceeds multi-head attention accuracy in a Conformer-Transducer ASR system while increasing throughput by up to 44 percent.

Pith tools