ALISA: An automatic lightly supervised speech segmentation and alignment tool. (January 2016)

• Record Type: Journal Article
• Authors: Stan, A.; Mamiya, Y.; Yamagishi, J.; Bell, P.; Watts, O.; Clark, R.A.J.; King, S.
• Is Part Of: Computer speech & language. Volume 35(2016)
• Page Start: 116
• Page End: 133
• Publication Date: 2016-01
• Subjects: Speech segmentation -- Speech and text alignment -- Grapheme acoustic models -- Lightly supervised system -- Imperfect transcripts; 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.2015.06.006
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract : Highlights: ALISA can align speech with imperfect transcripts in any alphabetic language. On average, 70% of the data is being correctly aligned, with a WER of less than 0.5%. Subjective listening tests showed a slight preference for the fully supervised system. Abstract: This paper describes the ALISA tool, which implements a lightly supervised method for sentence-level alignment of speech with imperfect transcripts. Its intended use is to enable the creation of new speech corpora from a multitude of resources in a language-independent fashion, thus avoiding the need to record or transcribe speech data. The method is designed so that it requires minimum user intervention and expert knowledge, and it is able to align data in languages which employ alphabetic scripts. It comprises a GMM-based voice activity detector and a highly constrained grapheme-based speech aligner. The method is evaluated objectively against a gold standard segmentation and transcription, as well as subjectively through building and testing speech synthesis systems from the retrieved data. Results show that on average, 70% of the original data is correctly aligned, with a word error rate of less than 0.5%. In one case, subjective listening tests show a statistically significant preference for voices built on the gold transcript, but this is small and in other tests, no statistically significant differences between the systems built from the fully supervised training data and the one which uses the proposed method are found.