Publication Details
Tuning phone decoders for language identification
Li Haizhou (IIR)
Tong Rong (IIR)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Phonotactic language identification, hidden Markov models, neural networks, mutual information, multilingual
This paper is on tuning phone decoders for language identification. In this work, we explore how language identification accuracy of a phone decoder can be enhanced.
Phonotactic approach, phone recognition to be followed by language modeling, is one of the most popular approaches to language identification (LID). In this work, we explore how language identification accuracy of a phone decoder can be enhanced by varying acoustic resolution of the phone decoder, and subsequently how multiresolution versions of the same decoder can be integrated to improve the LID accuracy. We use mutual information to select the optimum set of phones for a specific acoustic resolution. Further, we propose strategies for building multilingual systems suitable for LID applications, and subsequently fine tune these systems to enhance the overall accuracy.
@INPROCEEDINGS{FITPUB9302, author = "Pillai Chellappan Kumar Santhosh and Haizhou Li and Rong Tong and Pavel Mat\v{e}jka and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}", title = "Tuning phone decoders for language identification", pages = "5010--5013", booktitle = "Proc. International Conference on Acoustics, Speech, and Signal Processing 2010", journal = "Proc. International Conference on Acoustics, Speech, and Signal Processing", volume = 2010, number = 3, year = 2010, location = "Dallas, US", publisher = "IEEE Signal Processing Society", ISBN = "978-1-4244-4296-6", ISSN = "1520-6149", language = "english", url = "https://www.fit.vut.cz/research/publication/9302" }