Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles

[2506.01256] Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2506.01256 (eess) [Submitted on 2 Jun 2025 ( v1 ), last revised 13 Apr 2026 (this version, v4)] Title: Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles Authors: Matthew C. Kelley View a PDF of the paper titled Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles, by Matthew C. Kelley View PDF HTML (experimental) Abstract: Forced alignment is a common tool to align audio with orthographic and phonetic transcriptions. Most forced alignment tools provide only point-estimates of boundaries. The present project introduces a method of producing gradient boundaries by deriving confidence intervals using neural network ensembles. Ten different segment classifier neural networks were previously trained, and the alignment process is repeated with each classifier. The ensemble is then used to place the point-estimate of a boundary at the median of the boundaries in the ensemble, and the gradient range is placed using a 97.85% confidence interval around the median constructed using order statistics. Gradient boundaries are taken here as a more realistic representation of how segments transition into each other. Moreover, the range indicates the model uncertainty in the boundary placement, facilitating tasks like finding boundaries that should be reviewed. As a bonus, on the Buckeye and TIMIT corpora, the ensemble boundaries show a slight overall improvement over using just a single model. The gradient boundaries can be emitted during alignment as JSON files and a main table for programmatic and statistical analysis. For familiarity, they are also output as Praat TextGrids using a point tier to represent the edges of the boundary regions. Comments: accepted for publication; 12 pages, 4 figures Subjects: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD) Cite as: arXiv:2506.01256 [eess.AS] (or arXiv:2506.01256v4 [eess.AS] for this version) https://doi.org/10.48550/arXiv.2506.01256 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1515/phon-2025-0039 Focus to learn more DOI(s) linking to related resources Submission history From: Matthew C. Kelley [ view email ] [v1] Mon, 2 Jun 2025 02:12:28 UTC (550 KB) [v2] Mon, 26 Jan 2026 22:40:13 UTC (248 KB) [v3] Wed, 28 Jan 2026 06:01:52 UTC (248 KB) [v4] Mon, 13 Apr 2026 21:09:17 UTC (1,412 KB) Full-text links: Access Paper: View a PDF of the paper titled Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles, by Matthew C. Kelley View PDF HTML (experimental) TeX Source view license Current browse context: eess.AS < prev | next > new | recent | 2025-06 Change to browse by: cs cs.CL cs.LG cs.SD eess References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback#436435
• Noise-Adaptive Conformal Classification with Marginal Coverage#1082928
• Extreme metrics from large ensembles: investigating the effects of ensemble size on their estimates#1145670
• GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning#229439
• A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection#129249