Pith. sign in

REVIEW

M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper

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 2409.11889 v3 pith:LALH7HIO submitted 2024-09-18 cs.SD eess.AS

M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper

classification cs.SD eess.AS
keywords retrievalm2r-whisperaugmentationmulti-scalemulti-stageperformancerecognitionsentence-level
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

State-of-the-art models like OpenAI's Whisper exhibit strong performance in multilingual automatic speech recognition (ASR), but they still face challenges in accurately recognizing diverse subdialects. In this paper, we propose M2R-whisper, a novel multi-stage and multi-scale retrieval augmentation approach designed to enhance ASR performance in low-resource settings. Building on the principles of in-context learning (ICL) and retrieval-augmented techniques, our method employs sentence-level ICL in the pre-processing stage to harness contextual information, while integrating token-level k-Nearest Neighbors (kNN) retrieval as a post-processing step to further refine the final output distribution. By synergistically combining sentence-level and token-level retrieval strategies, M2R-whisper effectively mitigates various types of recognition errors. Experiments conducted on Mandarin and subdialect datasets, including AISHELL-1 and KeSpeech, demonstrate substantial improvements in ASR accuracy, all achieved without any parameter updates.

discussion (0)

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