Title: | Improving very large vocabulary language modeling and decoding for speech recognition in morphologically rich languages Menetelmiä laajan sanaston kielimallinnukseen ja puheentunnistukseen morfologisesti rikkaille kielille |
Author(s): | Varjokallio, Matti |
Date: | 2020 |
Language: | en |
Pages: | 86 + app. 136 |
Department: | Signaalinkäsittelyn ja akustiikan laitos Department of Signal Processing and Acoustics |
ISBN: | 978-952-64-0181-2 (electronic) 978-952-64-0180-5 (printed) |
Series: | Aalto University publication series DOCTORAL DISSERTATIONS, 208/2020 |
ISSN: | 1799-4942 (electronic) 1799-4934 (printed) 1799-4934 (ISSN-L) |
Supervising professor(s): | Kurimo, Mikko, Prof., Aalto University, Department of Signal Processing and Acoustics, Finland |
Thesis advisor(s): | Virpioja, Sami, Dr., University of Helsinki, Finland |
Subject: | Electrical engineering |
Keywords: | automatic speech recognition, morphologically rich languages, language modeling, psycholinguistics, automaattinen puheentunnistus, morfologisesti rikkaat kielet, kielimallinnus, psykolingvistiikka |
Archive | yes |
|
|
Abstract:Morfologisesti rikkaiden ja agglutinatiivisten kielten laajan sanaston puheentunnistuksen yksi haasteista on sanaston suuri koko. Tunnistussanaston täytyy monissa tunnistustehtävissä sisältää miljoonia sanamuotoja. |
|
Parts:[Publication 1]: Matti Varjokallio, Mikko Kurimo and Sami Virpioja. Learning a Subword Vocabulary Based on Unigram Likelihood. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, pages 7-12, December 2013. DOI: 10.1109/ASRU.2013.6707697 View at Publisher [Publication 2]: Matti Varjokallio and Mikko Kurimo. A Toolkit for Efficient Learning of Lexical Units for Speech Recognition. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), Reykjavik, Iceland, pages 3072-3075, May 2014[Publication 3]: Matti Varjokallio and Dietrich Klakow. Unsupervised Morph Segmentation and Statistical Language Models for Vocabulary Expansion. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL (Volume 2: Short Papers), Berlin, Germany, pages 175-180, August 2016. DOI: 10.18653/v1/P16-2029 View at Publisher [Publication 4]: Matti Varjokallio, Mikko Kurimo and Sami Virpioja. Class n-gram Models for Very Large Vocabulary Speech Recognition of Finnish and Estonian. Proceedings of the 4th International Conference on Statistical Language and Speech Processing, SLSP, Pilsen, Czech Republic, pages 133-144, October 2016. DOI: 10.1007/978-3-319-45925-7_11 View at Publisher [Publication 5]: Matti Varjokallio, Sami Virpioja and Mikko Kurimo. Morphologically Motivated Word Classes for Very Large Vocabulary Speech Recognition of Finnish and Estonian. Computer Speech & Language, volume 66, March 2021. DOI: 10.1016/j.csl.2020.101141 View at Publisher [Publication 6]: Matti Varjokallio and Mikko Kurimo. A Word-Level Token-Passing Decoder for Subword n-gram LVCSR. Proceedings of the 2014 IEEE Workshop on Spoken Language Technology, South Lake Tahoe, USA, pages 495-500, December 2014. DOI: 10.1109/SLT.2014.7078624 View at Publisher [Publication 7]: Mikko Kurimo, Seppo Enarvi, Ottokar Tilk, Matti Varjokallio, Andre Mansikkaniemi and Tanel Alumae. Modeling Under-Resourced Languagesfor Speech Recognition. Language Resources and Evaluation, volume 51, issue 4, pages 961-987, December 2017. Full text in Acrsi/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-201708036363. DOI: 10.1007/s10579-016-9336-9 View at Publisher [Publication 8]: Matti Varjokallio, Sami Virpioja and Mikko Kurimo. First-pass Techniques for Very Large Vocabulary Speech Recognition of Morphologically Rich Languages. Proceedings of the 2018 IEEE Workshop on Spoken Language Technology, Athens, Greece, pages 227-234, December 2018. DOI: 10.1109/SLT.2018.8639691 View at Publisher [Publication 9]: Minna Lehtonen, Matti Varjokallio, Henna Kivikari, Annika Hulten, Sami Virpioja, Tero Hakala, Mikko Kurimo, Krista Lagus and Riitta Salmelin. Statistical Models of Morphology Predict Eye-Tracking Measures During Visual Word Recognition. Memory & Cognition, volume 47, pages 1245-1269, October 2019. Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-201906033442. DOI:10.3758/s13421-019-00931-7 View at Publisher |
|
|
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