Pith. sign in

REVIEW 4 cited by

Why does CTC result in peaky behavior?

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 2105.14849 v2 pith:GO6ZHSPP submitted 2021-05-31 cs.LG cs.AIcs.CLcs.NEcs.SDeess.ASmath.STstat.TH

classification cs.LGcs.AIcs.CLcs.NEcs.SDeess.ASmath.STstat.TH
keywords behaviorpeakyanalysisconvergencefurtherlabelmodeloccurs
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The peaky behavior of CTC models is well known experimentally. However, an understanding about why peaky behavior occurs is missing, and whether this is a good property. We provide a formal analysis of the peaky behavior and gradient descent convergence properties of the CTC loss and related training criteria. Our analysis provides a deep understanding why peaky behavior occurs and when it is suboptimal. On a simple example which should be trivial to learn for any model, we prove that a feed-forward neural network trained with CTC from uniform initialization converges towards peaky behavior with a 100% error rate. Our analysis further explains why CTC only works well together with the blank label. We further demonstrate that peaky behavior does not occur on other related losses including a label prior model, and that this improves convergence.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. LCS-CTC: Leveraging Soft Alignments to Enhance Phonetic Transcription Robustness

    eess.AS 2025-08 conditional novelty 6.0 of 10

    LCS-CTC, a phoneme recognizer trained with similarity-aware LCS alignment masks constraining CTC, outperforms vanilla CTC on all reported PER, WPER, boundary-loss, and articulatory metrics.

  2. Analyzing the Importance of Blank for CTC-Based Knowledge Distillation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A symmetric blank-selection method for CTC knowledge distillation lets a student model train without any CTC loss and with no loss in word error rate.

  3. WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Wildcard CTC on intermediate encoder layers spots user-listed keywords at inference and biases later layers, improving unknown-word F1 by up to 29% relative without retraining or TTS modules.

  4. Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection

    eess.AS 2024-11 conditional novelty 4.0 of 10

    Adding a language-identification block trained with non-peaky CTC and injecting the resulting language posteriors reduces mixed-error rate on Mandarin-English SEAME by about 0.5 to 0.8 percent absolute over the D-MoE ...

Pith tools