In this paper we describe “Actors Challenge”: a web-based interactive game designed to collect massively multi-speaker, multi-lingual oral data on the connection between prosody and various aspects of meaning. Game participants take on the two roles of auditioners and casting directors. Auditioners are asked to record certain target phrases modulated according to the emotional or attitudinal profiles that correspond to contexts or stage cues given to them. They then switch roles and become Casting Directors. Now they have to listen to other participants’ recordings, guess the corresponding context/stage cue that the auditioner tried to convey, and evaluate how good the performance was. By having the players alternate between these two roles we obtain both data creation and data validation from the same set of participants. We expect that the final dataset of labeled recordings will be valuable for a range of applications: training multilingual Speech Emotion Recognition classifiers; discovering correlations and variations in prosodic patterns among unrelated languages; examining correlations between prosodic patterns and emotion recognizability; probing the possibility that some prosodic patterns are universal.
“Actors Challenge”: Collecting Data to Study Prosodic Patterns and Their Mappings to Meanings Across Languages / Sepanta, Sia Vosh; Chaiko, Natallia; Zamparelli, Roberto. - (2024), pp. 1-5. (Intervento presentato al convegno LREC COLING tenutosi a Turin nel 21st May 2024).
“Actors Challenge”: Collecting Data to Study Prosodic Patterns and Their Mappings to Meanings Across Languages
Sepanta, Sia Vosh;Chaiko, Natallia;Zamparelli, Roberto
2024-01-01
Abstract
In this paper we describe “Actors Challenge”: a web-based interactive game designed to collect massively multi-speaker, multi-lingual oral data on the connection between prosody and various aspects of meaning. Game participants take on the two roles of auditioners and casting directors. Auditioners are asked to record certain target phrases modulated according to the emotional or attitudinal profiles that correspond to contexts or stage cues given to them. They then switch roles and become Casting Directors. Now they have to listen to other participants’ recordings, guess the corresponding context/stage cue that the auditioner tried to convey, and evaluate how good the performance was. By having the players alternate between these two roles we obtain both data creation and data validation from the same set of participants. We expect that the final dataset of labeled recordings will be valuable for a range of applications: training multilingual Speech Emotion Recognition classifiers; discovering correlations and variations in prosodic patterns among unrelated languages; examining correlations between prosodic patterns and emotion recognizability; probing the possibility that some prosodic patterns are universal.File | Dimensione | Formato | |
---|---|---|---|
lrec-coling_Games_NLP_2024.pdf
accesso aperto
Descrizione: Short Paper
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Creative commons
Dimensione
742.84 kB
Formato
Adobe PDF
|
742.84 kB | Adobe PDF | Visualizza/Apri |
2024.games-1.1.pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Creative commons
Dimensione
1.35 MB
Formato
Adobe PDF
|
1.35 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione