pith. sign in

arxiv: 2603.06193 · v2 · pith:S3TL5CPFnew · submitted 2026-03-06 · 💻 cs.SD · cs.AI· eess.AS

Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding

classification 💻 cs.SD cs.AIeess.AS
keywords decodingwhisper-cdlong-formcontrastivelogitsmulti-negativerecognitionspeech
0
0 comments X
read the original abstract

Long-form speech recognition with large encoder-decoder models such as Whisper often exhibit hallucinations, repetition loops, and content omissions. These errors can accumulate and be further amplified when the previous segment's transcription is used as decoding context. We propose Whisper-CD, a training-free contrastive decoding framework that contrasts clean-audio logits against negative logits computed from three acoustically motivated perturbations: Gaussian noise injection, silence signal, and audio temporal shift. We aggregate these negatives via the log-sum-exp operator, building a unified multi-negative objective for token-by-token decoding. Across five English long-form benchmarks, Whisper-CD reduces WER by up to 24.3pp on CORAAL and shows 48% faster token generation throughput than beam search. Because Whisper-CD operates purely at inference time, it can be applied as a drop-in replacement to already-deployed Whisper systems without retraining.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 1 Pith paper

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

  1. Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations

    cs.CL 2026-06 unverdicted novelty 6.0

    Introduces ontology memory-augmented ASR correction that organizes prior interaction history into retrievable nodes and reports gains over direct correction in 9 of 10 backbone-setting pairs on a new long-context dataset.