On the Use of Differentiable Viterbi Decoding for Linear-Chain CRFs

Strahl S, Zeitler J, Müller M (2026)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2026

Pages Range: 396-400

Conference Proceedings Title: Proceedings of the European Signal Processing Conference (EUSIPCO)

Event location: Bruges, Belgium BE

Abstract

Linear-chain conditional random fields (CRFs) are widely used for sequence labeling, where local prediction scores are combined with a transition model to determine the most likely overall label sequence via Viterbi decoding. In modern learning-based systems, neural networks typically provide these local prediction scores, which are then combined by a CRF to improve temporal structure. Since Viterbi decoding is non-differentiable, it is difficult to integrate CRF-based modeling flexibly within end-to-end trainable pipelines. While prior work on dynamic programming provides a differentiable approximation of Viterbi decoding that alleviates this limitation, empirical studies of its behavior and practical use in CRF-based models remain limited. In this paper, we provide a practical description of differentiable Viterbi decoding and illustrate its behavior when applied to linear-chain CRFs. We refer to this differentiable CRF-based module as dCRF. We further demonstrate its use as an intermediate component within a larger, end-to-end trainable pipeline through a pitch class estimation case study, where dCRF serves as a module to enhance temporal structure in spectrogram-like representations. Compared to recurrent baselines, dCRF leads to similar results, while being more controllable and parameter-efficient.

Authors with CRIS profile

Sebastian Strahl International Audio Laboratories Erlangen (AudioLabs) Johannes Zeitler International Audio Laboratories Erlangen (AudioLabs) Meinard Müller Lehrstuhl für Semantische Audiosignalverarbeitung (AudioLabs)

How to cite

APA:

Strahl, S., Zeitler, J., & Müller, M. (2026). On the Use of Differentiable Viterbi Decoding for Linear-Chain CRFs. In Proceedings of the European Signal Processing Conference (EUSIPCO) (pp. 396-400). Bruges, Belgium, BE.

MLA:

Strahl, Sebastian, Johannes Zeitler, and Meinard Müller. "On the Use of Differentiable Viterbi Decoding for Linear-Chain CRFs." Proceedings of the European Signal Processing Conference (EUSIPCO), Bruges, Belgium 2026. 396-400.

BibTeX: Download