TU Darmstadt / ULB / TUbiblio

A domain-agnostic approach for opinion prediction on speech

Santos, Pedro Bispo ; Beinborn, Lisa ; Gurevych, Iryna
eds.: Nissim, Malvina ; Patti, Viviana ; Plank, Barbara (2016)
A domain-agnostic approach for opinion prediction on speech.
Osaka, Japan
Conference or Workshop Item, Bibliographie

Abstract

We explore a domain-agnostic approach for analyzing speech with the goal of opinion prediction. We represent the speech signal by mel-frequency cepstral coefficients and apply long short-term memory neural networks to automatically learn temporal regularities in speech. In contrast to previous work, our approach does not require complex feature engineering and works without textual transcripts. As a consequence, it can easily be applied on various speech analysis tasks for different languages and the results show that it can nevertheless be competitive to the state- of-the-art in opinion prediction. In a detailed error analysis for opinion mining we find that our approach performs well in identifying speaker-specific characteristics, but should be combined with additional information if subtle differences in the linguistic content need to be identified.

Item Type: Conference or Workshop Item
Erschienen: 2016
Editors: Nissim, Malvina ; Patti, Viviana ; Plank, Barbara
Creators: Santos, Pedro Bispo ; Beinborn, Lisa ; Gurevych, Iryna
Type of entry: Bibliographie
Title: A domain-agnostic approach for opinion prediction on speech
Language: English
Date: December 2016
Publisher: The COLING 2016 Organizing Committee
Book Title: Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media (PEOPLES)
Event Location: Osaka, Japan
URL / URN: http://www.aclweb.org/anthology/W16-4318
Corresponding Links:
Abstract:

We explore a domain-agnostic approach for analyzing speech with the goal of opinion prediction. We represent the speech signal by mel-frequency cepstral coefficients and apply long short-term memory neural networks to automatically learn temporal regularities in speech. In contrast to previous work, our approach does not require complex feature engineering and works without textual transcripts. As a consequence, it can easily be applied on various speech analysis tasks for different languages and the results show that it can nevertheless be competitive to the state- of-the-art in opinion prediction. In a detailed error analysis for opinion mining we find that our approach performs well in identifying speaker-specific characteristics, but should be combined with additional information if subtle differences in the linguistic content need to be identified.

Uncontrolled Keywords: reviewed;UKP_reviewed;UKP_p_AudioVisual
Identification Number: TUD-CS-2016-14666
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Date Deposited: 31 Dec 2016 14:29
Last Modified: 24 Jan 2020 12:03
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details