Less Peaky and More Accurate CTC Forced Alignment by Label Priors

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 allevia...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-07
Main Authors: Huang, Ruizhe, Zhang, Xiaohui, Ni, Zhaoheng, Sun, Li, Hira, Moto, Hwang, Jeff, Manohar, Vimal, Vineel Pratap, Wiesner, Matthew, Watanabe, Shinji, Povey, Daniel, Khudanpur, Sanjeev
Format: Article
Language:English
Subjects:
Alignment
Automatic speech recognition
Labels
Phonemes
Word boundaries
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422