A hybrid refinement scheme for intra- and cross- corpora phonetic segmentation. (January 2015)

• Record Type: Journal Article
• Authors: Zhao, Sixuan; Soon, Ing Yann; Koh, Soo Ngee; Luke, Kang Kwong
• Is Part Of: Computer speech & language. Volume 29(2015)
• Page Start: 81
• Page End: 97
• Publication Date: 2015-01
• Subjects: Phonetic segmentation -- Statistical correction -- Multi-resolution -- Predictive model -- Cross-corpora segmentation; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2014.08.001
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A hybrid refinement scheme for phonetic segmentation is proposed. Statistical correction is applied to improve segmentation results. Multi-resolution fusion leads to higher segmentation accuracy. Refinements based on predictive models further reduce segmentation errors. Cross-corpora segmentation can be improved by the hybrid refinement scheme. Abstract: This paper proposes a hybrid refinement scheme for more accurate localization of phonetic boundaries by combining three different post-processing techniques, including statistical correction, fusion, and predictive models. A statistical method based on state-level correction is proposed to improve the segmentation results. Effects of search ranges on the statistical correction process are studied and a state selection scheme is used to enhance the correction results. This paper also examines the effects of time resolution, i.e., stepsize, of acoustic models on the accuracy of segmentation. A multi-resolution fusion process is proposed to further refine the statistically corrected results. Finally, predictive models are designed to improve the segmentation accuracy by incorporating various acoustic features and searching around the preliminary boundary with a smaller stepsize. By applying the hybrid refinement scheme on a well-known corpus, significant improvements of segmentation results in terms of segmentation accuracy with different tolerances, mean absolute error (MAE), and root-mean-square error (RMSE) can be observed. Furthermore, a scenario of cross-corpora segmentation is examined in generating the segmentation results for a new corpus with a small set of labeled data. Experimental results show that the proposed refinement procedure can generate segmentation results comparable to those given by well-trained acoustic models obtained from the new corpus.