• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Human Laughter Generation using Hybrid Generative Models

Vol. 15, No. 5, May 31, 2021
10.3837/tiis.2021.05.001, Download Paper (Free):

Abstract

Laughter is one of the most important nonverbal sound that human generates. It is a means for expressing his emotions. The acoustic and contextual features of this specific sound are different from those of speech and many difficulties arise during their modeling process. During this work, we propose an audio laughter generation system based on unsupervised generative models: the autoencoder (AE) and its variants. This procedure is the association of three main sub-process, (1) the analysis which consist of extracting the log magnitude spectrogram from the laughter database, (2) the generative models training, (3) the synthesis stage which incorporate the involvement of an intermediate mechanism: the vocoder. To improve the synthesis quality, we suggest two hybrid models (LSTM-VAE, GRU-VAE and CNN-VAE) that combine the representation learning capacity of variational autoencoder (VAE) with the temporal modelling ability of a long short-term memory RNN (LSTM) and the CNN ability to learn invariant features. To figure out the performance of our proposed audio laughter generation process, objective evaluation (RMSE) and a perceptual audio quality test (listening test) were conducted. According to these evaluation metrics, we can show that the GRU-VAE outperforms the other VAE models.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
N. Mansouri and Z. Lachiri, "Human Laughter Generation using Hybrid Generative Models," KSII Transactions on Internet and Information Systems, vol. 15, no. 5, pp. 1590-1609, 2021. DOI: 10.3837/tiis.2021.05.001.

[ACM Style]
Nadia Mansouri and Zied Lachiri. 2021. Human Laughter Generation using Hybrid Generative Models. KSII Transactions on Internet and Information Systems, 15, 5, (2021), 1590-1609. DOI: 10.3837/tiis.2021.05.001.

[BibTeX Style]
@article{tiis:24633, title="Human Laughter Generation using Hybrid Generative Models", author="Nadia Mansouri and Zied Lachiri and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2021.05.001}, volume={15}, number={5}, year="2021", month={May}, pages={1590-1609}}