Pith. sign in

REVIEW 1 cited by

Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation

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 2204.02470 v2 pith:54OG4ZBG submitted 2022-04-05 cs.CL cs.SDeess.AS

classification cs.CLcs.SDeess.AS
keywords speechdomainmodelsdataextractorsresourcetaskscombining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the relatedness between the SSL training domain(s) and the target data domain. On the contrary, spectral feature (SF) extractors such as log Mel-filterbanks are hand-crafted non-learnable components, and could be more robust to domain shifts. The present work examines the assumption that combining non-learnable SF extractors to SSL models is an effective approach to low resource speech tasks. We propose a learnable and interpretable framework to combine SF and SSL representations. The proposed framework outperforms significantly both baseline and SSL models on Automatic Speech Recognition (ASR) and Speech Translation (ST) tasks on three low resource datasets. We additionally design a mixture of experts based combination model. This last model reveals that the relative contribution of SSL models over conventional SF extractors is very small in case of domain mismatch between SSL training set and the target language data.

Discussion (0). Sign in 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. Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection

    cs.SD 2025-07 conditional novelty 4.0 of 10

    Fusing CQCC spectral features with Wav2Vec2.0 embeddings via cross-attention lowers average equal error rate from 10.87% to 6.80% across four speech deepfake benchmarks.

Pith tools