Automatic speech recognition in machine-aided translation

Brown, Peter F.; Chen, S.F.; Pietra, Stephen A. Della; Pietra, Vincent J. Della; Kehler, Andrew; Mercer, R.L.

doi:10.1006/csla.1994.1008

Cited by 42 publications

(47 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of the Statistical Speech Language Translation is to translate a given acoustic observation vector = … into a target sentence = … [16] [27]. The methodology used in our proposal is based on the definition of a function Pr that returns the probability that is a translation of a given acoustic observation [28] [29].…”

Section: Language Translation Systemmentioning

confidence: 99%

“…There are two main ways for adapting the speech recognition module (SRM) using the SAPI interface [16]. SAPI adaptation uses specific calls to the SAPI interface.…”

Section: Speech Recognition Adaptationmentioning

confidence: 99%

“…Between the projects that use additional information sources we find TransTalk project [15] and an IBM project [16]. Both projects are dictation systems for translators that have the destination language signal voice (provided by a human) and the text of the source language.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Language Translation Systemmentioning

confidence: 99%

“…There are two main ways for adapting the speech recognition module (SRM) using the SAPI interface [16]. SAPI adaptation uses specific calls to the SAPI interface.…”

Section: Speech Recognition Adaptationmentioning

confidence: 99%

See 1 more Smart Citation

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

show abstract

“…al [1] and Brown et. al [2] proposed to improve the recognition performance of such an ASR system in the case of a given source language document. They used machine translation (MT) techniques for improving the target language ASR system for the human translator with the help This work has been funded in part by the European Union under the integrated project TC-Star -Technology and Corpora for Speech to Speech Translation -(IST-2002-FP6-506738, http://www.tc-star.org).…”

Section: Introductionmentioning

confidence: 99%

Speech translation enhanced automatic speech recognition

Paulik

Stüker

Fügen

et al. 2005

IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.

View full text Add to dashboard Cite

Nowadays official documents have to be made available in many languages, like for example in the EU with its 20 official languages. Therefore, the need for effective tools to aid the multitude of human translators in their work becomes easily apparent. An ASR system, enabling the human translator to speak his translation in an unrestricted manner, instead of typing it, constitutes such a tool. In this work we improve the recognition performance of such an ASR system on the target language of the human translator by taking advantage of an either written or spoken source language representation. To do so, machine translation techniques are used to translate between the different languages and then the involved ASR systems are biased towards the gained knowledge. We present an iterative approach for ASR improvement and outperform our baseline system by a relative word error rate reduction of 35.8% / 29.9% in the case of a written / spoken source language representation. Further, we show how multiple target languages, as for example provided by different simultaneous translators during European Parliament debates, can be incorporated into our system design for an improvement of all involved ASR systems.

show abstract

“…Indeed, the framework for closed-captions described above is directly analogous to the use of a translation model to aid a speech decoder for machine-aided translation, as proposed in [2,3]. Just as a translator's workstation might incorporate a statistical translation model together with an acoustic model so that the translator can dictate his translations, we can imagine that a transcriber's workstation would be equipped with a statistical closed-caption model, to enable highly accurate and fast dictation of news broadcast transcriptions.…”

Section: Introductionmentioning

confidence: 99%

Cheating with imperfect transcripts

Placeway

Lafferty²

Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

View full text Add to dashboard Cite

Most speech recognition systems try to reconstruct a word sequence given an acoustic input, using prior information about the language being spoken. In some cases, there is more information available to the decoder than simply the acoustics. When decoding a television news broadcast, for example, the closed-caption information that is often recorded for hearing impaired viewers may also be available. While these captions are generally not completely accurate transcriptions, they can be considered to be a strong hint as to what was actually spoken.In this paper, we present a formalization of this problem in terms of the source channel paradigm. We propose a simple translation model for mapping caption sequences to word sequences which updates the language model with the prior information inherent in the captions. We also describe an efficient implementation of the search in a Viterbi decoder, and present results using this system in the broadcast news domain.

show abstract

Automatic speech recognition in machine-aided translation

Cited by 42 publications

References 0 publications

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

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

Speech translation enhanced automatic speech recognition

Cheating with imperfect transcripts

Contact Info

Product

Resources

About