ACL Findings2026
Spectral Gravity Formant Estimation for Phonetic Segmentation
Abstract
Recent automated transcription systems have focused on end-to-end orthographic approaches driven by deep neural networks and sequence-to-sequence transformers. Growing public interest in transcription at the phonemic or phonetic level has led to re-purposing these systems to segment and identify phones, the basic sounds which comprise human speech. However, they miss the mark on a fundamental component of time-series analysis, namely time. For linguistic applications which require high fidelity in the temporal domain, the loss of timing information is untenable. Our work proposes a deadline-bounded expectation maximization (EM) algorithm with a novel initialization method to estimate formants, i.e., salient speech frequencies, for enhanced phonetic segmentation. Based on the concept of spectral gravity, i.e., treating spectral energy as mass attenuated by the square of frequency distance across the spectrum, our technique outperforms the recent state of the art on key clustering metrics, generating reasonable alignments across multiple languages with no a priori training.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on2
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, Michael AuliNeurIPS 2020 · 9,451 citations
- Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic SegmentationMichael S. Yantosca, Albert M. K. ChengACL 2025
Related papers
- LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form SpeechBingshen Mu, Xian Shi, Xiong Wang, Hexin Liu et al.ACL 2026 · 5 citations
- Listening Between the Frames: Bridging Temporal Gaps in Large Audio-Language ModelsHualei Wang, Yiming Li, Shuo Ma, Hong Liu et al.AAAI 2026 · 4 citations
- Revisiting the Entropy Semiring for Neural Speech RecognitionOscar Chang, Dongseong Hwang, Olivier SiohanICLR 2023 · 1 citation
- Generative Annotation for ASR Named Entity CorrectionYuanchang Luo, Daimeng Wei, Shaojun Li, Hengchao Shang et al.EMNLP 2025
- TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal GroundingMingyue Huo, Yiwen Shao, Yuheng ZhangACL 2026 · 12 citations
