Multilingual Speech Recognition
Alex Waibel,Hagen Soltau,Tanja Schultz,Thomas Schaaf,Florian Metze +4 more
- 01 Jan 2000
- pp 33-45
TL;DR: In this article, the authors describe the challenges of multilingual speech recognition and presents different solutions to the problem of automatic language identification task, which results in a flexible and user-friendly multilingual spoken dialog system.
read more
Abstract: The speech-to-speech translation system Verbmobil requires a multilingual setting. This consists of recognition engines in the three languages German, English and Japanese that run in one common framework together with a language identification component which is able to switch between these recognizers. This article describes the challenges of multilingual speech recognition and presents different solutions to the problem of the automatic language identification task. The combination of the described components results in a flexible and user-friendly multilingual spoken dialog system.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multilingual representations for low resource speech recognition and keyword search
Jia Cui,Brian Kingsbury,Bhuvana Ramabhadran,Abhinav Sethy,Kartik Audhkhasi,Xiaodong Cui,Ellen Kislal,Lidia Mangu,Markus Nussbaum-Thom,Michael Picheny,Zoltán Tüske,Pavel Golik,Ralf Schlüter,Hermann Ney,Mark J. F. Gales,Kate Knill,Anton Ragni,Haipeng Wang,P.C. Woodland +18 more
- 11 Sep 2015
TL;DR: This paper examines the impact of multilingual acoustic representations on Automatic Speech Recognition (ASR) and keyword search (KWS) for low resource languages in the context of the OpenKWS15 evaluation of the IARPA Babel program and shows that these multilingual representations significantly improve ASR and KWS performance.
Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning
Yulia Tsvetkov,Sunayana Sitaram,Manaal Faruqui,Guillaume Lample,Patrick Littell,David R. Mortensen,Alan W. Black,Lori Levin,Chris Dyer +8 more
- 01 Jun 2016
TL;DR: This work applies polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to be predicted to the problem of modeling phone sequences.
Mobile Speech-to-Speech Translation of Spontaneous Dialogs: An Overview of the Final Verbmobil System
Wolfgang Wahlster
- 01 Jan 2000
TL;DR: It is concluded that Verbmobil has successfully met the project goals with more than 80% of approximately correct translations and a 90% success rate for dialog tasks.
57
Efficient handling of multilingual language models
Christian Fügen,Sebastian Stüker,Hagen Soltau,Florian Metze,Tanja Schultz +4 more
- 30 Nov 2003
TL;DR: A new language model method is presented that allows for the combination of several monolingual into one multilingual language model and the techniques for building a multilingual speech recognizer are extended to the concept of grammars.
Towards universal speech recognition
Zhirong Wang,Umut Topkara,Tanja Schultz,Alex Waibel +3 more
- 14 Oct 2002
TL;DR: A universal speech recognition system that is trained by sharing speech and text data across languages and thus reduces the number of parameters and overhead significantly at the cost of only slight accuracy loss is described.
References
•Proceedings Article
Proceedings of the International Conference on Acoustics Speech and Signal Processing
Stefan Bilbao,Kevin Arcas,Antoine Chaigne +2 more
- 01 Jan 2006
546
Automatic language identification
M.A. Zissman,Kay Berkling +1 more
TL;DR: The set of available cues for language identification of speech is described and the different approaches to building working systems are discussed, including a range of historical approaches, contemporary systems that have been evaluated on standard databases, and promising future approaches.
197
Confidence measures for spontaneous speech recognition
Thomas Schaaf,Thomas Kemp +1 more
- 21 Apr 1997
TL;DR: The development of the measure of the confidence tagger JANKA, which is able to provide confidence information for the words at the output of the speech recognizer JANUS-3-SR, is described.
The Karlsruhe-Verbmobil speech recognition engine
Michael Finke,Petra Geutner,H. Hild,Thomas Kemp,Klaus Ries,Martin Westphal +5 more
- 21 Apr 1997
TL;DR: The Janus Speech Recognition Toolkit underlying the speech recognizer is introduced and the word error rate on the German spontaneous scheduling task (GSST) could be decreased from 30%word error rate in 1995 to 13.8% in 1996.
LVCSR-based language identification
Tanja Schultz,I. Rogina,Alex Waibel +2 more
- 07 May 1996
TL;DR: A language identification module for German, English, Spanish, and Japanese is built which yields 84% identification rate on the spontaneous scheduling task (SST) and can be used as a front end for the multilingual speech-to-speech translation system JANUS-II.