We report results on the AVEC-2014 depression dataset and find that individual systems range from 9.18 to 11.87 in root mean squared error (RMSE), and from 7.68 ...

Nov 1, 2014 · We report results on the AVEC-2014 depression dataset and find that individual systems range from 9.18 to 11.87 in root mean squared error (RMSE) ...

Dec 31, 2013 · We explore a diverse set of features based only on spoken audio to understand which features correlate with self-reported depression scores.

Nov 7, 2014 · We explore a diverse set of features based only on spoken audio to understand which features correlate with self-reported depression scores ...

Features are modeled using a variety of approaches, including support vector regression, a Gaussian backend and decision trees. We report results on the AVEC- ...

We report results on the AVEC-2014 depression dataset and find that individual systems range from 9.18 to 11.87 in root mean squared error (RMSE), and from 7.68 ...

The SRI AVEC-2014 Evaluation System ... We explore a diverse set of features based only on spoken audio to understand which features correlate with self-reported ...

We report results on the AVEC-2014 depression dataset and find that individual systems range from 9.18 to 11.87 in root mean squared error (RMSE), and from 7.68 ...

A novel approach that combines unsupervised learning, knowledge transfer and hierarchical attention for the task of speech-based depression severity ...

Proceedings of the 4th International Workshop on Audio/Visual Emotion Challenge, AVEC '14, Orlando, Florida, USA, November 7, 2014.