Pith. sign in

REVIEW 2 cited by

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 2509.02830 v1 pith:GI22ES2A submitted 2025-09-02 cs.CL eess.AS

SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR

Pu Wang , Shinji Watanabe , Hugo Van hamme This is my paper
classification cs.CL eess.AS
keywords speechfine-tuningadaptationbenchmarkingdomainespnetmethodsparameter-efficient
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Parameter-efficient fine-tuning (PEFT) has emerged as a scalable solution for adapting large foundation models. While low-rank adaptation (LoRA) is widely used in speech applications, its state-of-the-art variants, e.g., VeRA, DoRA, PiSSA, and SVFT, are developed mainly for language and vision tasks, with limited validation in speech. This work presents the first comprehensive integration and benchmarking of these PEFT methods within ESPnet. We further introduce structured SVD-guided (SSVD) fine-tuning, which selectively rotates input-associated right singular vectors while keeping output-associated vectors fixed to preserve semantic mappings. This design enables robust domain adaptation with minimal trainable parameters and improved efficiency. We evaluate all methods on domain-shifted speech recognition tasks, including child speech and dialectal variation, across model scales from 0.1B to 2B. All implementations are released in ESPnet to support reproducibility and future work.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

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

  1. GC-LoRA: Gated Convolutional LoRA for Parameter-Efficient Acoustic Adaptation

    eess.AS 2026-06 unverdicted novelty 6.0

    GC-LoRA introduces a gated convolutional adapter into LoRA for efficient adaptation of transformer speech models to domain-specific acoustics, reporting up to 10.9% WER reduction on diverse test sets.

  2. Parameter-Efficient Continual Learning for Automatic Speech Recognition

    eess.AS 2026-06 unverdicted novelty 5.0

    A PECL method for ASR partitions weight matrices via singular values, adapts only via rotations in the tail subspace, and averages rotations across tasks to reduce forgetting while outperforming baselines on two benchmarks.