Prosodic Representations of Prominence Classification Neural Networks and Autoencoders Using Bottleneck Features

Show full item record



Permalink

http://hdl.handle.net/10138/312019

Citation

Kakouros , S , Suni , A , Šimko , J & Vainio , M 2019 , Prosodic Representations of Prominence Classification Neural Networks and Autoencoders Using Bottleneck Features . in 20th Annual Conference of the International Speech Communication Association (INTERSPEECH 2019) : Crossroads of Speech and Language . Interspeech , ISCA , Baixas , pp. 1946-1950 , Annual Conference of the International-Speech-Communication-Association , Graz , Austria , 15/09/2019 . https://doi.org/10.21437/Interspeech.2019-2984

Title: Prosodic Representations of Prominence Classification Neural Networks and Autoencoders Using Bottleneck Features
Author: Kakouros, Sofoklis; Suni, Antti; Šimko, Juraj; Vainio, Martti
Contributor: University of Helsinki, Department of Digital Humanities
University of Helsinki, Phonetics
University of Helsinki, Phonetics
University of Helsinki, Phonetics
Publisher: ISCA
Date: 2019
Language: eng
Number of pages: 5
Belongs to series: 20th Annual Conference of the International Speech Communication Association (INTERSPEECH 2019) Crossroads of Speech and Language
Belongs to series: Interspeech
URI: http://hdl.handle.net/10138/312019
Abstract: Prominence perception has been known to correlate with a complex interplay of the acoustic features of energy, fundamental frequency, spectral tilt, and duration. The contribution and importance of each of these features in distinguishing between prominent and non-prominent units in speech is not always easy to determine, and more so, the prosodic representations that humans and automatic classifiers learn have been difficult to interpret. This work focuses on examining the acoustic prosodic representations that binary prominence classification neural networks and autoencoders learn for prominence. We investigate the complex features learned at different layers of the network as well as the 10-dimensional bottleneck features (BNFs), for the standard acoustic prosodic correlates of prominence separately and in combination. We analyze and visualize the BNFs obtained from the prominence classification neural networks as well as their network activations. The experiments are conducted on a corpus of Dutch continuous speech with manually annotated prominence labels. Our results show that the prosodic representations obtained from the BNFs and higher-dimensional non-BNFs provide good separation of the two prominence categories, with, however, different partitioning of the BNF space for the distinct features, and the best overall separation obtained for F0.
Subject: 6121 Languages
6161 Phonetics
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
2984.pdf 1.850Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record