Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Prosodic Feature Generation for Back-Channel Prediction

Thamar Solorio, Olac Fuentes, Nigel G. Ward, Yaffa Al Bayyari

University of Texas at El Paso, USA

Using prosodic information to predict when back-channels are appropriate in spontaneous dialogs has become somewhat of a reference problem for automatic discovery techniques. Here we present experiments with two ideas: the use of features derived from randomly generated pitch and energy filters, and the use of instance-based learning, specifically the Locally Weighted Linear Regression (LWLR) algorithm. For the task of predicting possible back-channel locations in Iraqi Arabic [6], we obtain 22% precision and 51% recall, which is as good as that obtained using a laboriously developed and hand-tuned rule.

Full Paper

Bibliographic reference.  Solorio, Thamar / Fuentes, Olac / Ward, Nigel G. / Bayyari, Yaffa Al (2006): "Prosodic feature generation for back-channel prediction", In INTERSPEECH-2006, paper 1724-Thu1FoP.11.