RT info:eu-repo/semantics/doctoralThesis
T1 Design and evaluation of mobile computer-assisted pronunciation training tools for second language learning
A1 Tejedor García, Cristian
A2 Universidad de Valladolid. Escuela de Ingenierías Industriales
K1 Reconocimiento automático de voz
K1 Pronunciación
K1 33 Ciencias Tecnológicas
AB The quality of speech technology (automatic speech recognition, ASR, and textto-speech, TTS) has considerably improved and, consequently, an increasing numberof computer-assisted pronunciation (CAPT) tools has included it. However, pronunciationis one area of teaching that has not been developed enough since thereis scarce empirical evidence assessing the effectiveness of tools and games that includespeech technology in the field of pronunciation training and teaching. ThisPhD thesis addresses the design and validation of an innovative CAPT system forsmart devices for training second language (L2) pronunciation. Particularly, it aimsto improve learner’s L2 pronunciation at the segmental level with a specific set ofmethodological choices, such as learner’s first and second language connection (L1–L2), minimal pairs, a training cycle of exposure–perception–production, individualisticand social approaches, and the inclusion of ASR and TTS technology. Theexperimental research conducted applying these methodological choices with realusers validates the efficiency of the CAPT prototypes developed for the four mainexperiments of this dissertation. Data is automatically gathered by the CAPT systemsto give an immediate specific feedback to users and to analyze all results. Theprotocols, metrics, algorithms, and methods necessary to statistically analyze anddiscuss the results are also detailed. The two main L2 tested during the experimentalprocedure are American English and Spanish. The different CAPT prototypes designedand validated in this thesis, and the methodological choices that they implement,allow to accurately measuring the relative pronunciation improvement of theindividuals who trained with them. Both rater’s subjective scores and CAPT’s objectivescores show a strong correlation, being useful in the future to be able to assessa large amount of data and reducing human costs. Results also show an intensivepractice supported by a significant number of activities carried out. In the case of thecontrolled experiments, students who worked with the CAPT tool achieved betterpronunciation improvement values than their peers in the traditional in-classroominstruction group. In the case of the challenge-based CAPT learning game proposed,the most active players in the competition kept on playing until the end andachieved significant pronunciation improvement results.
YR 2020
FD 2020
LK http://uvadoc.uva.es/handle/10324/43663
UL http://uvadoc.uva.es/handle/10324/43663
LA eng
NO Departamento de Informática (Arquitectura y Tecnología de Computadores, Ciencias de la Computación e Inteligencia Artificial, Lenguajes y Sistemas Informáticos)
DS UVaDOC
RD 27-dic-2024