Title: | Language models for automatic speech recognition : construction and complexity control Kielimallit automaattisessa puheentunnistuksessa: luonti ja kompleksisuuden hallinta |
Author(s): | Siivola, Vesa |
Date: | 2007-09-03 |
Language: | en |
Pages: | 74, [66] |
Department: | Department of Computer Science and Engineering Tietotekniikan osasto |
ISBN: | 978-951-22-8894-6 |
Series: | Helsinki University of Technology dissertations in computer and information science. Report D, 21 |
ISSN: | 1459-7020 |
Subject: | Education, Computer science |
Keywords: | language model, speech recognition, subword unit, morpheme segmentation, variable order n-gram model, pruning, growing, state-space language model, kielimalli, puheentunnistus, sanapala, morfeemeihin jako, vaihtelevanasteinen n-grammimalli, karsiminen, kasvattaminen, tila-avaruuskielimalli |
OEVS yes | |
|
|
Abstract:Kielimalli on yksi avainosa suurisanastoisessa jatkuvan puheen tunnistusjärjestelmässä. Valtavia tekstiaineistoja on saatavilla kielimallien opettamiseen. Tässä väitöstyössä tutkitaan, miten opetusaineistosta löydetään oleelliset asiat ja miten ne voidaan esittää tiiviisti mallissa. |
|
Parts:Vesa Siivola, Teemu Hirsimäki, Mathias Creutz, and Mikko Kurimo. Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner. In Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech 2003), pages 2293-2296, Geneva, Switzerland, September 2003. [article1.pdf] © 2003 by authors.Teemu Hirsimäki, Mathias Creutz, Vesa Siivola, Mikko Kurimo, Sami Virpioja, and Janne Pylkkönen. Unlimited vocabulary speech recognition with morph language models applied to Finnish. Computer Speech and Language, volume 20 (4), pages 515-541, 2006.Vesa Siivola and Bryan L. Pellom. Growing an n-gram language model. In Proceedings of the 9th European Conference on Speech Communication and Technology (Interspeech 2005), pages 1309-1312, Lisbon, Portugal, September 2005. [article3.pdf] © 2005 by authors.Vesa Siivola, Teemu Hirsimäki, and Sami Virpioja. On growing and pruning Kneser–Ney smoothed N-Gram models. IEEE Transactions on Audio, Speech, and Language Processing, volume 15 (5), pages 1617-1624, 2007. [article4.pdf] © 2007 IEEE. By permission.Vesa Siivola. Language modeling based on neural clustering of words. Technical report IDIAP-COM 00-02, IDIAP, Martigny, Switzerland, 2000.Vesa Siivola and Antti Honkela. A state-space method for language modeling. In Proceedings of the 8th IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2003), pages 548-553, St. Thomas, U.S. Virgin Islands, November 2003. [article6.pdf] © 2003 IEEE. By permission. |
|
|
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Page content by: Aalto University Learning Centre | Privacy policy of the service | About this site