Pith. sign in

REVIEW 2 cited by

DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model

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 2303.09278 v1 pith:HLBD7FP4 submitted 2023-03-16 eess.AS cs.SD

classification eess.AScs.SD
keywords modeldistillationdistillw2v2makestreaminglossnon-streamingsmaller
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Wav2vec 2.0 (W2V2) has shown impressive performance in automatic speech recognition (ASR). However, the large model size and the non-streaming architecture make it hard to be used under low-resource or streaming scenarios. In this work, we propose a two-stage knowledge distillation method to solve these two problems: the first step is to make the big and non-streaming teacher model smaller, and the second step is to make it streaming. Specially, we adopt the MSE loss for the distillation of hidden layers and the modified LF-MMI loss for the distillation of the prediction layer. Experiments are conducted on Gigaspeech, Librispeech, and an in-house dataset. The results show that the distilled student model (DistillW2V2) we finally get is 8x faster and 12x smaller than the original teacher model. For the 480ms latency setup, the DistillW2V2's relative word error rate (WER) degradation varies from 9% to 23.4% on test sets, which reveals a promising way to extend the W2V2's application scope.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates

    cs.SD 2025-05 conditional novelty 5.0 of 10

    A per-layer learnable threshold, trained jointly with CTC fine-tuning, prunes 60-65% of parameters from wav2vec2-base and HuBERT-large without a statistically significant WER increase on test-clean.

  2. Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models

    cs.SD 2025-05 conditional novelty 5.0 of 10

    A small trained 'seed' speech encoder can be unfolded to several logical depths by repeating shared layers, matching independently trained models with up to 35% parameter reduction.

Pith tools