TY - GEN
T1 - Deep neural networks for anger detection from real life speech data
AU - Deng, Jun
AU - Eyben, Florian
AU - Schuller, Björn
AU - Burkhardt, Felix
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - There has been a lot of previous work on deep neural networks for automatic speech recognition, however, little emphasis has been placed on an investigation of effective deep learning architectures for anger detection from speech. In this paper, inspired by the state-of-the-art deep learning algorithms, we propose a variant of Deep Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs), Convolution Neural Networks (CNNs) with 3 × 3 kernels, and LSTM RNNs combined with CNNs, in conjunction with log-mel filter bank features and brute forced low-level-descriptors from the standardised ComParE set for speech anger detection. We extensively evaluate the deep networks on a big real-life speech corpus of 26 970 utterances with utterance-level labels collected from a German voice portal, finding that our proposed neural networks significantly outperform traditional modelling algorithms for speech anger detection.
AB - There has been a lot of previous work on deep neural networks for automatic speech recognition, however, little emphasis has been placed on an investigation of effective deep learning architectures for anger detection from speech. In this paper, inspired by the state-of-the-art deep learning algorithms, we propose a variant of Deep Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs), Convolution Neural Networks (CNNs) with 3 × 3 kernels, and LSTM RNNs combined with CNNs, in conjunction with log-mel filter bank features and brute forced low-level-descriptors from the standardised ComParE set for speech anger detection. We extensively evaluate the deep networks on a big real-life speech corpus of 26 970 utterances with utterance-level labels collected from a German voice portal, finding that our proposed neural networks significantly outperform traditional modelling algorithms for speech anger detection.
UR - http://www.scopus.com/inward/record.url?scp=85047271370&partnerID=8YFLogxK
U2 - 10.1109/ACIIW.2017.8272614
DO - 10.1109/ACIIW.2017.8272614
M3 - Conference contribution
AN - SCOPUS:85047271370
T3 - 2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017
SP - 1
EP - 6
BT - 2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017
Y2 - 23 October 2017 through 26 October 2017
ER -