The Development of an Advanced SLP-based System for the Individual Learning and Fast Training of Speaking Skills in a New Foreign Language Planning the Graduate College Research Program ìChinese for German Engineers (and other L1-speakers of German)î

This paper describes the organization of a concerted action of German and Chinese phoneticians, IT speech technologists and specialists in the eld of foreign language teaching in order to create a new research program which has been proposed by the rst author as a so-called graduate college (entitled iChinesisch fr deutsche Ingenieure und andere L1-Sprecher des Deutscheni) to the Federal Government of Germany. The paper has four parts: We rst start by describing the prime goals and conditions of our application-oriented basic research plans for the development of a new SL/T-system (Speech Learning/Training-system). Then we argue why o in phonetic speech research o the classic paradigm of ianalysis-by-synthesisi should be replaced by a the programmatic approach which follows the new isynthesis-by-analysisi-principle. In the third part we look at certain types of teaching speech acts and teaching dialogs. In the last part we will be trying to consider the fact that such complex approaches of application-oriented basic speech research programs as in our case needs a concerted effort in the collaboration of all relevant disciplines within the eld of SLP (including also NLP 1 ), and here we end with the question of how the so-called dilemma of text-tospeech developers can be systematically avoided by practically involving the addressed users of the developed System (engineers and language students) from the very beginning.

[1]  Nicole Beringer,et al.  The quality of multilingual automatic segmentation using German MAUS , 2000, INTERSPEECH.

[2]  H. Pfitzinger,et al.  Applying the Munich Parametric High Definition ( PHD ) Speech Synthesis System to the Problem of Teaching Chinese Tones to L 1-Speakers of German , 2004 .

[3]  Hartmut R. Pfitzinger,et al.  Parametric high definition (PHD) speech synthesis-by-analysis: the development of a fundamentally new system creating connected speech by modifying lexically-represented language units , 2000, INTERSPEECH.

[4]  Zongji Wu,et al.  FROM TRADITIONAL CHINESE PHONOLOGY TO MODERN SPEECH PROCESSING —— REALIZATION OF TONE AND INTONATION IN STANDARD CHINESE —— , 2000 .

[5]  Keikichi Hirose.  Accent Type Recognition of Japanese Using Perceived Mora Pitch Values and Its Use for Pronunciation Training System , 2004 .

[6]  Bernd Pompino-Marschall,et al.  Theoretical principles concerning segmentation, labelling strategies and levels of categorical annotation for spoken language database systems , 1993, EUROSPEECH.

[7]  Hartmut R. Pfitzinger,et al.  An IPA vowel diagram approach to analysing L1 effects on vowel production and perception , 2002, INTERSPEECH.

[8]  J. Flege.  Second Language Speech Learning Theory , Findings , and Problems , 2006 .

[9]  Rodolfo Delmonte,et al.  SLIM prosodic automatic tools for self-learning instruction , 2000, Speech Commun..

[10]  Chian Chuu.  LIESHOU : A Mandarin Conversational Task Agent for the Galaxy-II Architecture , 2003 .

[11]  W. Strange.  Speech perception and linguistic experience : issues in cross-language research , 1995 .

[12]  B. Pompino-Marschall,et al.  Categorical Perception of Speaker Identity , 1984 .

[13]  Shinobu Masaki,et al.  Learning-induced neural plasticity associated with improved identification performance after training of a difficult second-language phonetic contrast , 2003, NeuroImage.