Forced Alignment

Follow this topic Ask about this topic

Latest papers

9 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Noise-Robust Forced Alignment for Spontaneous Speech
Oct 15, 2026Laurin Wagner, Mario ZusagForced Alignment Speech Processing
nyra labs, Vienna, Austria
Where Words Begin and End
Oct 13, 2026Husein ZolkepliForced Alignment Audio-Text Alignment
Scicom (MSC) Berhad, Malaysia
FuseAlign: Forced Alignment in the Wild
Sep 27, 2026Mithilesh Vaidya, Stephen Bailey, Sumukh Badam +2Forced Alignment Audio-Text Alignment
Descript, Inc.
FA-Bench: A Benchmark for Phone- and Word-Level Timestamp Accuracy in Forced Alignment and ASR on Clean and Noisy Speech
Sep 26, 2026Wei Chu, Yuanzhe Dong, Ke Tan +11Forced Alignment ASR Evaluation
Olewave, USA · Stanford University · Cartesia +5
Scaling Forced Alignment to End-User Devices
Sep 17, 2026Lawry Sorenson, Michael Crandall, Eric K. Ringger +1Forced Alignment Audio-Text Alignment
Brigham Young University Computer Science Department Provo, UT, United States
Evaluation of forced alignment of code-mixed speech: the case of Hindi-English
Jul 28, 2026Ayushi Pandey, Pamir Gogoi, Kevin TangCode-Switching Speech Recognition Code-Switching
Karya, India · Department of English Language and Linguistics, Institute of English and American Studies, Faculty of Arts and Humanities, Heinrich Heine University Düsseldorf, Germany · Department of Linguistics, University of Florida, United States of America
Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming
Jun 24, 2026Rotem Rousso, Eyal Cohen, Joseph KeshetForced Alignment
Montreal Forced Aligner and the state of speech-to-text alignment in 2026
Jun 16, 2026Michael McAuliffe, Kaylynn Gunter, Michael Wagner +1Forced Alignment Speech Processing
University of Wisconsin–Madison, USA · McGill University and Centre for Brain, Language, and Music, Canada · University of Oregon, USA
A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment
Feb 26, 2026Zarif Ishmam, Zarif Mahir, Shafnan Wasif +1Voice Activity Detection Forced Alignment
Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh

Oct 15, 2026J/K move · Enter open · S save

Noise-Robust Forced Alignment for Spontaneous Speech

Laurin Wagner, Mario Zusag

nyra labs, Vienna, Austria

Forced Alignment Speech Processing Hidden Markov Models

Open paper AskPDF arXiv

We show that forced aligners degrade on spontaneous, noisy real-world speech, and that fillers, laughter, and disfluencies corrupt word boundaries, impacting many downstream applications. We revisit the classical GMM-HMM aligner with upsampled WavLM features instead of MFCCs, explicit phone units for fillers and non-lexical vocal events trained on verbatim-annotated spontaneous speech, and a discriminative projection fitted on clean and noise-corrupted feature pairs to improve robustness. The pipeline is self-bootstrapped from 149h of curated audio without manual or external boundary targets. On conversational (Buckeye) and disfluent (FluencyBank) speech it reaches word-boundary MAEs of 20.6 and 76.9ms, 19% and 17% lower than the strongest of ten baselines. Catastrophic misalignments (>200ms) are 2.7 times rarer than Montreal Forced Aligners (MFA) best model even after widening MFA's search beam, which we show removes a large pruning artifact from its conversational error; event units halve the error next to laughter, while being meaningfully more robust than existing aligners.