INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association Dresden, Germany September 6-10, 2015

Audio Quotation Marks for Natural Language Understanding

Simon Boutin (1), Réal Tremblay (2), Patrick Cardinal (1), Doug Peters (2), Pierre Dumouchel (1)

(1) École de Technologie Supérieure, Canada
(2) Nuance Communications, Canada

Detecting the presence of quotations in speech is a difficult task for automatic natural language understanding. This paper presents a study on the correlation between three prosodic features present in a voice command and the presence or absence of quotations. These features consist of intra-word pause durations, F₀ reset and F₀ continuity. A combination of lexical and prosodic extraction tools was used to extract these features. The two-sample Kolmogorov-Smirnov test was then used to compare the distributions of the collected measures. The results show a correlation between these features and the presence or absence of quotations. Moreover, the results show that it is possible to use these features to differentiate direct from indirect quotations.

Full Paper

Bibliographic reference.  Boutin, Simon / Tremblay, Réal / Cardinal, Patrick / Peters, Doug / Dumouchel, Pierre (2015): "Audio quotation marks for natural language understanding", In INTERSPEECH-2015, 1349-1352.