The Role of Phonetics in Speech to Speech Translation

Although first demonstrators for speech to speech translation have been presented, they are still ‘show cases’ with lacking robustness for everyday usage. This lacking robustness is caused by the insufficient performance of the building blocks of speech to speech translation systems i.e. of speech recognition, spoken language translation and speech synthesis. In the context of a phonetic conference the question arises if phonetic knowledge can contribute to improve substantially speech to speech translation technology. This paper addresses this problem and gives an introduction to the ICPhS symposium ‘the role of phonetics in speech to speech translation’. Based on a review on the current use of phonetic knowledge in speech to speech translation technology and based on a review of unsolved problems in speech recognition, synthesis and spoken language translation this paper emphasize the need of suited language resources and the need for a research in the articulatory acoustic space.