logo Idiap Research Institute        
 [BibTeX] [Marc21]
A Neural Model to Predict Parameters for a Generalized Command Response Model of Intonation
Type of publication: Conference paper
Citation: Schnell_INTERSPEECH2018_2018
Publication status: Accepted
Booktitle: Proc. Interspeech 2018
Year: 2018
Month: September
Pages: 3147-3151
DOI: /10.21437/interspeech.2018-1904
Abstract: The Generalised Command Response (GCR) model is a time-local model of intonation that has been shown to lend itself to (cross-language) transfer of emphasis. In order to generalise the model to longer prosodic sequences, we show that it can be driven by a recurrent neural network emulating a spiking neural network. We show that a loss function for error backpropagation can be formulated analogously to that of the Spike Pattern Association Neuron (SPAN) method for spiking networks. The resulting system is able to generate prosody comparable to a state-of-the-art deep neural network implementation, but potentially retaining the transfer capabilities of the GCR model.
Projects Idiap
Authors Schnell, Bastian
Garner, Philip N.
Crossref by Schnell_MLSLP-18_2018
Added by: [UNK]
Total mark: 0
  • Schnell_INTERSPEECH2018_2018.pdf