PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 22, 20240 citationsOpen Access

Less Peaky and More Accurate CTC Forced Alignment by Label Priors

View Full Paper
RHRuizhe HuangXZXiaohui ZhangZNZhaoheng Ni

Key Points

Key points are not available for this paper at this time.

Abstract

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Huang et al. (2024) studied this question.

synapsesocial.com/papers/68e6e3dbb6db64358765f0b8https://doi.org/10.48550/arxiv.2406.02560
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Less Peaky and More Accurate CTC Forced Alignment by Label Priors2024 · 10 citations
  2. 2A CTC-Aligned Lightweight Korean TTS Pipeline without External Aligners2026
  3. 3BFA: Real-time Multilingual Text-to-speech Forced Alignment2025
  4. 4A Framework for Phoneme-Level Pronunciation Assessment Using CTC2024 · 9 citations
  5. 5I like your tone: The effects of phonological similarity versus model training hours on cross-language forced alignment in tonal languages2025