Speech-to-speech translation based on finite-state transducers

Casacuberta, Francisco; Llorens, D.; Martínez, César; Molau, Sirko; Nevado, Francisco; Ney, Hermann; Pastor, María Luisa Carrió; Picó, David; Sanchís, Alberto; Vidal, Enrique; Vilar, Juan Miguel

doi:10.1109/icassp.2001.940906

Cited by 22 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presentation here is based on work carried out in the framework of the EUTRANS project (Casacuberta et al 2001) and the VERBMOBIL project (Wahlster 2000).…”

Section: Resultsmentioning

confidence: 99%

Stochastic Modelling: From Pattern Classification to Speech Recognition and Language Translation

Ney

1999

Informatik Aktuell

View full text Add to dashboard Cite

This paper gives an overview of the stochastic modelling approach to machine translation.Starting with the Bayes decision rule as in pattern classification and speech recognition, we show how the resulting system architecture can be structured into three parts: the language model probability, the string translation model probability and the search procedure that generates the word sequence in the target language. We discuss the properties of the system components and report results on the translation of spoken dialogues in the VERBMOBIL project. The experience obtained in the VERB-MOBIL project, in particular a largescale end-to-end evaluation, showed that the stochastic modelling approach resulted in significantly lower error rates than three competing translation approaches: the sentence error rate was 29% in comparison with 52% to 62% for the other translation approaches.

show abstract

“…The presentation here is based on work carried out in the framework of the EUTRANS project (Casacuberta et al 2001) and the VERBMOBIL project (Wahlster 2000).…”

Section: Resultsmentioning

confidence: 99%

Stochastic Modelling: From Pattern Classification to Speech Recognition and Language Translation

Ney

1999

Informatik Aktuell

View full text Add to dashboard Cite

show abstract

“…The simplest way to do speech translation is to first recognize the speech, then produce the most likely hypothesis and to translate it as done in the previous section. In the literature various approaches for closer coupling have been proposed that can be roughly divided into two principles: techniques based on finite-state transducers [16,3,4,7] and techniques based on n-best or lattice representations of the transcribed speech signal [13,17,12]. For this work an n-best interface is used.…”

Section: Interaction Between Transcription and Translationmentioning

confidence: 99%

Investigating translation of Parliament speeches

Déchelotte

Schwenk

Gauvain

et al. 2005

IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.

View full text Add to dashboard Cite

This paper reports on recent experiments for speech to text (STT) translation of European Parliamentary speeches. A Spanish speech to English text translation system has been built using data from the TC-STAR European project. The speech recognizer is a state-of-the-art multipass system trained for the Spanish EPPS task and the statistical translation system relies on the IBM-4 model. First, MT results are compared using manual transcriptions and 1-best ASR hypotheses with different word error rates. Then, an n-best interface between the ASR and MT components is investigated to improve the STT process. Derivation of the fundamental equation for machine translation suggests that the source language model is not necessary for STT. This was investigated by using weak source language models and by n-best rescoring adding the acoustic model score only. A significant loss in the BLEU score was observed suggesting that the source language model is needed given the insufficiencies of the translation model. Adding the source language model score in the n-best rescoring process recovers the loss and slightly improves the BLEU score over the 1-best ASR hypothesis. The system achieves a BLEU score of 37.3 with an ASR word error rate of 10% and a BLEU score of 40.5 using the manual transcripts.

show abstract

“…EUTRANS system, in [14], was made using the methodologies developed and the data collected during the project. The speech translation is built in a similar way as speech recognition.…”

Section: Introductionmentioning

confidence: 99%

“…Other interface between automatic speech recognition and machine translation are the confusion networks. The authors in [14] also describe the advantages of using these networks. On one side confusion networks permit to effectively represent a huge number of transcription hypotheses, on the other side they lead to a very efficient search algorithm for statistical machine translation.…”

Section: Introductionmentioning

confidence: 99%

Statistical speech translation system based on voice recognition optimization using multimodal sources of knowledge and characteristics vectors

Cánovas

Tomás

Lloret

et al. 2013

Computer Standards & Interfaces

View full text Add to dashboard Cite

Abstract-Synergic combination of different sources of knowledge is a key issue for the development of modern statistical translators. Reconnaissance, and thus the translation, can be improved by adding new heuristic characteristics. In this work, a speech translation statistical system that adds additional other-than-voice information in a voice translation system is presented. The additional information serves as a base for the loglinear combination of several statistical models. We obtain the characteristics vectors using a statistical model that is based on the N-best reconnaissance list. We describe the theoretical framework of the problem, summarize the overall architecture of the system, and show how the system is enhanced with the additional information. Our real prototype implements a real-time speech translation system from Spanish to English that is adapted to specific teaching-related environments. Finally, we will provide and explain the system performance results. A tool like the one presented in this article may increase the participation rate of the foreign students to the lecture classes and talks.

show abstract

Speech-to-speech translation based on finite-state transducers

Cited by 22 publications

References 6 publications

Stochastic Modelling: From Pattern Classification to Speech Recognition and Language Translation

Stochastic Modelling: From Pattern Classification to Speech Recognition and Language Translation

Investigating translation of Parliament speeches

Statistical speech translation system based on voice recognition optimization using multimodal sources of knowledge and characteristics vectors

Contact Info

Product

Resources

About