Pith. sign in

REVIEW 3 cited by

Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2301.13003 v2 pith:37L7M4LW submitted 2023-01-30 cs.CL cs.AIcs.SDeess.AS

Minglun Han , Feilong Chen , Jing Shi , Shuang Xu , Bo Xu This is my paper · ORCID
classification cs.CLcs.AIcs.SDeess.AS
keywords knowledgeplmsdistillationmodelslanguagecif-basedhierarchicallevel
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. Leveraging the capabilities of PLMs to enhance automatic speech recognition (ASR) systems has also emerged as a promising research direction. However, previous works may be limited by the inflexible structures of PLMs and the insufficient utilization of PLMs. To alleviate these problems, we propose the hierarchical knowledge distillation (HKD) on the continuous integrate-and-fire (CIF) based ASR models. To transfer knowledge from PLMs to the ASR models, HKD employs cross-modal knowledge distillation with contrastive loss at the acoustic level and knowledge distillation with regression loss at the linguistic level. Compared with the original CIF-based model, our method achieves 15% and 9% relative error rate reduction on the AISHELL-1 and LibriSpeech datasets, respectively.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. DESign: Dynamic Context-Aware Convolution and Efficient Subnet Regularization for Continuous Sign Language Recognition

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A sign language recognition model using context-aware dynamic convolutions and subnetwork CTC regularization reports new state-of-the-art word error rates on PHOENIX14, PHOENIX14-T, and CSL-Daily.

  2. Scaling Properties of Diffusion Models for Perceptual Tasks

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Diffusion models for depth, optical flow, and amodal segmentation improve along power laws as training and test-time compute scale, and the fitted recipes match prior specialist models with less data.

  3. Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR

    eess.AS 2025-05 conditional novelty 5.0 of 10

    GM-OT, a fused Wasserstein and Gromov-Wasserstein graph-matching alignment for BERT-to-acoustic knowledge transfer, reports 3.98% CER on AISHELL-1 test versus 5.76% for a Conformer+CTC baseline.

Pith tools