Spoken language processing in a multilingual context

@article{Lamel1996SpokenLP,
  title={Spoken language processing in a multilingual context},
  author={Lori Lamel and Martine Adda-Decker and Jean-Luc Gauvain and Gilles Adda},
  journal={Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96},
  year={1996},
  volume={4},
  pages={2203-2206 vol.4}
}
  • L. Lamel, M. Adda-Decker, G. Adda
  • Published 3 October 1996
  • Linguistics
  • Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96
The authors overview the spoken language processing activities at LIMSI, which are carried out in a multilingual framework. These activities include speech-to-text conversion, spoken language systems for information retrieval, speaker and language recognition, and speech response. The Spoken Language Processing Group has also been actively involved in corpora development and evaluation. The group has regularly participated in evaluations organized by ARPA, in the LE-SQALE project, and in the… 
9 Citations

Figures and Tables from this paper

A Critical Review of State-OfThe-Art Technologies forCross-Language Speech

TLDR
A critical review of the state-of-the-art of technologies for speech retrieval in cross-language environments and some possible experimental paradigms are outlined.

A Critical Review of State-OfThe-Art Technologies for Cross-Language Speech Retrieval

  • J.F.
  • Computer Science
  • 2002
TLDR
A critical review of the state-of-the-art of technologies for speech retrieval in cross-la~lguage environments and outlines some possible experimental paradigms are given.

A Critical Review of State-Of-The-Art Technologies for Cross-Language Speech Retrieval

TLDR
A critical review of the state-of-the-art of technologies for speech retrieval in cross-la~lguage environments and outlines some possible experimental paradigms are given.

Some Issues in Speech Recognizer Portability

TLDR
Some of the main issues in porting a recognizer to another task or language are addressed, and some some recent research activities aimed at reducing the porting cost and at developing generic core speech recognition technology are highlighted.

Multilingual and crosslingual acoustic modelling for automatic speech recognition

TLDR
Two major aspects of multilingual and crosslingual acoustic modelling are focused on: acoustic model definition and acoustic model adaptation.

Text-To-Phoneme Mapping Using Neural Networks

TLDR
The problem of text-to-phoneme mapping using neural networks is stud- in this thesis, and the complexity/speed of the model training is of secondary importance compared to e.g., the speed of convergence or model size.

Approches empiriques et modélisation statistique de la parole. (Empirical methods and statistical modeling of speech)

TLDR
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not, for teaching and research institutions in France or abroad, or from public or private research centers.

Approches empiriques et modélisation statistique de la parole

Ce document decrit a la fois un parcours en modelisation statistique du langage et son application aux systemes multilingues de traitement de la langue, ou je relate mes travaux de recherches sur 28

References

SHOWING 1-10 OF 32 REFERENCES

Development of spoken language corpora for travel information

TLDR
This paper reports on the ongoing work in developing spoken language corpora in the context of information access in two travel domain tasks, L’ATIS and MASK, and examines the user-friendliness, reliability, ease-of-use of the MASK data.

Issues in Large Vocabulary, Multilingual Speech Recognition

TLDR
The existing recognizer for American English and French, has been ported to British English and German and has been assessed in the context of the LRE SQALE project whose objective was to experiment with installing in Europe a multilingual evaluation paradigm for the assessment of large vocabulary, continuous speech recognition systems.

BREF, a large vocabulary spoken corpus for French

TLDR
This paper presents some of the design considerations of BREF, a large read-speech corpus for French designed to provide continuous speech data for the development of dictation machines, for the evaluation of continuous speech recognition systems, and for the study of phonological variations.

Speaker-independent continuous speech dictation

WSJCAMO: a British English speech corpus for large vocabulary continuous speech recognition

TLDR
The motivation for the corpus, the processes undertaken in its construction and the utilities needed as support tools are described, and comparative results on these tasks for British and American English are concluded.

Continuous speech dictation in French

TLDR
This paper reports on efforts in large vocabulary, speaker-independent continuous speech recognition of French using the BREF corpus and makes use of continuous density HMM with Gaussian mixture for acoustic modeling and n-gram statistics estimated on 38 million words of newspaper text from Le Monde for language modeling.

The LIMSI continuous speech dictation system

TLDR
The LIMSI recognizer which was evaluated in the ARPA NOV93 CSR test is described, and experimental results on the WSJ and BREF corpora under closely matched conditions are reported.

A stochastic case frame approach for natural language understanding

TLDR
An evaluation methodology is used that assesses performance at different semantic levels, including the database response comparison used in the ARPA ATIS paradigm, and replaces the system of rules for the semantic analysis with a relatively simple first-order hidden Markov model.

Developments in large vocabulary, continuous speech recognition of German

TLDR
This large vocabulary continuous speech recognition system for the German language, the development of which was partly carried out within the context of the European LRE project 62-058 SQALE, achieves a word error rate of 17.3% on the ger-eval95 test set.

Developments in continuous speech dictation using the ARPA WSJ task

TLDR
Experimental results for development and evaluation test data are given, as well as an analysis of the errors on the development data.