Prosodic tools for language learning

Abstract

In this paper we will be concerned with the role played by prosody in language learning and by the speech technology already available as commercial product or as prototype, capable to cope with the task of helping language learner in improving their knowledge of a second language from the prosodic point of view. The paper has been divided into two separate sections: Section One, dealing with Rhythm and all related topics; Section Two dealing with Intonation. In the Introduction we will argue that the use of ASR (Automatic Speech Recognition) as Teaching Aid should be under-utilized and should be targeted to narrowly focussed spoken exercises, disallowing openended dialogues, in order to ensure consistency of evaluation. Eventually, we will support the conjoined use of ASR technology and prosodic tools to produce GOP useable for linguistically consistent and adequate feedback to the student. This will be illustrated by presenting State of the Art for both sections, with systems well documented in the scientific literature of the respective field.In order to discuss the scientific foundations of prosodic analysis we will present data related to English and Italian and make comparisons to clarify the issues at hand. In this context, we will also present the Prosodic Module of a courseware for computer-assisted foreign language learning called SLIM-an acronym for Multimedia Interactive Linguistic Software, developed at the University of Venice (Delmonte et al. in Convegno GFS-AIA, pp. 47-58, 1996a; Ed-Media 96, AACE, pp. 326-333, 1996b). The Prosodic Module has been created in order to deal with the problem R. Delmonte ( ) Linguistic Computational Laboratory (LCL), Università Ca' Foscari-Ca' Bembo, Dorsoduro, 1075-30123 Venezia, Italy e-mail: delmont@unive.it url: project.cgm.unive.it of improving a student's performance both in the perception and production of prosodic aspects of spoken language activities. It is composed of two different sets of Learning Activities, the first one dealing with phonetic and prosodic problems at word level and at syllable level; the second one dealing with prosodic aspects at phonological phrase and utterance suprasegmental level. The main goal of Prosodic Activities is to ensure consistent and pedagogically sound feedback to the student intending to improve his/her pronunciation in a foreign language.

Speech Processing for Language Learning: A Practical Approach to Computer-Assisted Pronunciation Teaching

“…ASR incorporating neural networks, probabilistic classifiers and decision making schemes, such as GMM, HMM and SVM, is one of the most effective technologies for CAPT design. Yet, some discrete precautions should be taken to apply ASR in a controlled CAPT environment [38]. A case in point is the unsuitability of ASR for automatic evaluation of learner input.…”

Adopting StudyIntonation CAPT Tools to Tonal Languages Through the Example of Vietnamese

“…Computer-Assisted Prosody Teaching (CAPT) tools integrated with various speech processing technologies make it possible to obtain pitch plots so that to provide a visual representation of the speech. From a number of research works, we learn that, within L2 learning activities, training enhanced by such a visualization of pitch contours has a positive effect on learner's pronunciation (e. g., [9,10]). In particular, the authors of [11] conducted an interesting study, where they used speech analysis software (Praat) to present a visual display of the Chinese native speaker's pitch curves for learners, then asked learners to record themselves repeating the same words and compare their pitch contours with those of the native speaker.…”

Speech and Language Technologies

“…i.e. there is no need to refer to G. What (30) shows is that as N grows, the probability of getting previously unseen samples decreases linearly. Furthermore, the probability of the new sample to be equal to θ k is equal to (α 0 + N) −1 N k .…”