# Less Peaky and More Accurate CTC Forced Alignment by Label Priors

arXiv: https://arxiv.org/abs/2406.02560 · HTML: https://mlsanity.com/paper/2406.02560/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 14 of 14)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition](https://mlsanity.com/paper/2007.09127/) (2020)
- [Why does CTC result in peaky behavior?](https://mlsanity.com/paper/2105.14849/) (2021)
- [TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch](https://mlsanity.com/paper/2310.17864/) (2023)
- [Phone-to-audio alignment without text: A Semi-supervised Approach](https://mlsanity.com/paper/2110.03876/) (2021)
- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)
- [NeuFA: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism](https://mlsanity.com/paper/2203.16838/) (2022)
- [On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models](https://mlsanity.com/paper/2107.04154/) (2021)

## Built on by (most cited first, 12 of 12)

- [CR-CTC: Consistency regularization on CTC for improved speech recognition](https://mlsanity.com/paper/2410.05101/) (2024)
- [SSR: Alignment-Aware Modality Connector for Speech Language Models](https://mlsanity.com/paper/2410.00168/) (2024)
- [Whisper Has an Internal Word Aligner](https://mlsanity.com/paper/2509.09987/) (2025)
- [CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment](https://mlsanity.com/paper/2602.19574/) (2026)
- [DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition](https://mlsanity.com/paper/2501.19010/) (2025)
- [Segmentation-free Goodness of Pronunciation](https://mlsanity.com/paper/2507.16838/) (2025)
- [Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs](https://mlsanity.com/paper/2607.06831/) (2026)
- [Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection](https://mlsanity.com/paper/2412.08651/) (2024)
- [Analyzing the Importance of Blank for CTC-Based Knowledge Distillation](https://mlsanity.com/paper/2506.01503/) (2025)
- [OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesis](https://mlsanity.com/paper/2602.22949/) (2026)
- [Modeling Overlapped Speech with Shuffles](https://mlsanity.com/paper/2603.17769/) (2026)
- [Scaling Forced Alignment to End-User Devices](https://mlsanity.com/paper/2609.21145/) (2026)

## Abstract (arXiv)

Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), especially at finer granularity, e.g., phoneme level. This paper aims at alleviating the peaky behavior for CTC and improve its suitability for forced alignment generation, by leveraging label priors, so that the scores of alignment paths containing fewer blanks are boosted and maximized during training. As a result, our CTC model produces less peaky posteriors and is able to more accurately predict the offset of the tokens besides their onset. It outperforms the standard CTC model and a heuristics-based approach for obtaining CTC's token offset timestamps by 12-40% in phoneme and word boundary errors (PBE and WBE) measured on the Buckeye and TIMIT data. Compared with the most widely used FA toolkit Montreal Forced Aligner (MFA), our method performs similarly on PBE/WBE on Buckeye, yet falls behind MFA on TIMIT. Nevertheless, our method has a much simpler training pipeline and better runtime efficiency. Our training recipe and pretrained model are released in TorchAudio.