A new relational paradigm is proposed that is based on voice shapes, which represent the speech style used to establish an effective communication. The functional voice shapes are: "rounded", which means that a colloquial and empath communication is established; "triangular", which means transmitting energy, joy and interest; "squared", which highlights competence and solidity. The dysfunctional shapes are: "flat", a monotone style that does not capture the listener attention; "spiky", which is an aggressive style that transmits anger or blame towards the listener. An attempt has been made to match the voice shapes to acoustic features of the vocal signal, starting from parameters extracted from the recordings of 12 actors that have reproduced the voice shapes. Preliminary results allowed a subset of the estimated parameters to be identified that have shown good capabilities in discriminating the voice shapes. These parameters are related to distributions of voicing and silence periods, pitch and Cepstral Peak Prominence Smoothed. A web campaign has been also launched asking untrained subjects to "give their voice to the research". Even though only two voice shapes have been identified in this data set, a comparison with the parameters extracted from the trained subjects has shown a good agreement.
A new paradigm of effective communication based on voice shapes / Carullo, A.; Anibaldi, A.; Astolfi, A.; Atzori, A.; Cennamo, V.; Zito, G.. - ELETTRONICO. - 2019-:(2019), pp. 7781-7788. (Intervento presentato al convegno 23rd International Congress on Acoustics: Integrating 4th EAA Euroregio, ICA 2019 tenutosi a Aachen , Germany nel 9-13 September 2019) [10.18154/RWTH-CONV-238940].
A new paradigm of effective communication based on voice shapes
Carullo A.;Astolfi A.;Atzori A.;Cennamo V.;
2019
Abstract
A new relational paradigm is proposed that is based on voice shapes, which represent the speech style used to establish an effective communication. The functional voice shapes are: "rounded", which means that a colloquial and empath communication is established; "triangular", which means transmitting energy, joy and interest; "squared", which highlights competence and solidity. The dysfunctional shapes are: "flat", a monotone style that does not capture the listener attention; "spiky", which is an aggressive style that transmits anger or blame towards the listener. An attempt has been made to match the voice shapes to acoustic features of the vocal signal, starting from parameters extracted from the recordings of 12 actors that have reproduced the voice shapes. Preliminary results allowed a subset of the estimated parameters to be identified that have shown good capabilities in discriminating the voice shapes. These parameters are related to distributions of voicing and silence periods, pitch and Cepstral Peak Prominence Smoothed. A web campaign has been also launched asking untrained subjects to "give their voice to the research". Even though only two voice shapes have been identified in this data set, a comparison with the parameters extracted from the trained subjects has shown a good agreement.File | Dimensione | Formato | |
---|---|---|---|
769351.pdf
accesso aperto
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
460.93 kB
Formato
Adobe PDF
|
460.93 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2941152