2020 INTERSPEECH INTERSPEECH 2020

Phonetic Entrainment in Cooperative Dialogues: A Case of Russian

Abstract

It has been shown for a number of languages that speakers accommodate to each other in conversation. Such accommodation, or entrainment, reveals itself in many modalities including speech: interlocutors are found to entrain in intensity, fundamental frequency, tempo and other acoustic features. This paper presents data on speech entrainment in Russian using the standard measures for speech entrainment: proximity, convergence and synchrony. The research uses 49 dialogues from the SibLing speech corpus where speakers played a card-matching game. The list of acoustic features includes various measures of pitch, energy, spectral slope, HNR, jitter, and shimmer. The results for Russian are compared with those published previously for other languages.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
🧭 Keyword Pioneer — phonetic entrainment
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Robotics, Speech & Audio