Investigation of golden speakers for second language learners from imitation preference perspective by voice modification

This paper investigates what voice features (e.g., speech rate and pitch-formants) make a teacher's voice preferable for second language learners to imitate, when they practice sentence pronunciation using Computer-Assisted Pronunciation Training (CAPT) systems. The CAPT system employed in our investigation uses a single teacher's voice as the source to automatically resynthesize several sample voices with different voice features based on the features of a learner's voice. Our approach is different from that in the study conducted by Probst et al. which uses multiple native speakers' voices as sample voices [Probst, K., Ke, Y., Eskenazi, M., 2002. Enhancing foreign language tutors - in search of the golden speaker. Speech Communication 37 (3-4), 161-173]. Our approach can reduce the influence of characteristics of teachers' voices (e.g., voice quality and clarity) on the investigation. Our experimental results show that a teacher's voice, which has similar speech rate and pitch-formants to a learner's voice, is not always the learner's first imitation preference. Many factors can influence learners' imitation preferences, e.g., background and proficiency of the language that they are learning. Also, a learner's preferences may change at different learning stages. We thus advocate an automatic voice modification function in CAPT systems to provide speech learning material with a wide variety of voice features, e.g., different speech rates or different pitch-formants. Learners then can control the voice modifications according to their preferences.