Distributed representation of melodic contours

Daniil Kocharov, Alla Menshikova

We introduce a new computational model for melodic contours - melody embeddings. It is based on the approach of distributional semantics where embeddings represent units as continuous vectors in a multi-dimensional space based on hypothesis that units with similar meaning are used in similar contexts. This paradigm is applied to melodic contours and their segments. Melodic contours are represented by vectors of the same dimensionality independent on their length and shape. We successfully evaluated the ability of proposed model to measure the distance between melodic contours. The results of applying the model for a task of prominent words detection have not showed the improvement over traditional prosodic features. Nevertheless we assume the model to be very promising. The possible applications for the proposed unsupervised prosodic model include processing of speech of under-resourced languages, modelling prosodic variability for text-to-speech synthesis, recognition and classification of prosodic events by means of deep-learning algorithms.

 DOI: 10.21437/SpeechProsody.2018-34

Cite as: Kocharov, D., Menshikova, A. (2018) Distributed representation of melodic contours. Proc. 9th International Conference on Speech Prosody 2018, 167-171, DOI: 10.21437/SpeechProsody.2018-34.

  author={Daniil Kocharov and Alla Menshikova},
  title={Distributed representation of melodic contours},
  booktitle={Proc. 9th International Conference on Speech Prosody 2018},