Abstract
Human-machine addressee detection (H-M AD) is a modern paralinguistics and dialogue challenge that arises in multiparty conversations between several people and a spoken dialogue system (SDS) since the users may also talk to each other and even to themselves while interacting with the system. The SDS is supposed to determine whether it is being addressed or not. All existing studies on acoustic H-M AD were conducted on corpora designed in such a way that a human addressee and a machine played different dialogue roles. This peculiarity influences speakers’ behaviour and increases vocal differences between human- and machine-directed utterances. In the present study, we consider the Restaurant Booking Corpus (RBC) that consists of complexity-identical human- and machine-directed phone calls and allows us to eliminate most of the factors influencing speakers’ behaviour implicitly. The only remaining factor is the speakers’ explicit awareness of their interlocutor (technical system or human being). Although complexity-identical H-M AD is essentially more challenging than the classical one, we managed to achieve significant improvements using data augmentation (unweighted average recall (UAR) = 0.628) over native listeners (UAR = 0.596) and a baseline classifier presented by the RBC developers (UAR = 0.539).
Highlights
Spoken dialogue systems (SDSs) appeared a couple of decades ago and have already become part of our everyday life
Complexity-identical human-machine addressee detection (H-M AD) is essentially more challenging than the classical one, we managed to achieve significant improvements using data augmentation (unweighted average recall (UAR) = 0.628) over native listeners (UAR = 0.596) and a baseline classifier presented by the Restaurant Booking Corpus (RBC) developers (UAR = 0.539)
E.g., Siri, Cortana, Alexa, and Alisa, are typical examples of modern spoken dialogue system (SDS). Such systems face the problem of human-machine addressee detection (H-M AD) that arises in multiparty spoken conversations between several people and an Sensors 2020, 20, 2740; doi:10.3390/s20092740
Summary
Spoken dialogue systems (SDSs) appeared a couple of decades ago and have already become part of our everyday life. Speech is the most natural way of communication between people, and they usually prefer speech-based user interfaces over textual and graphical input alone when it comes to natural interaction with technical systems [1]. Considerable progress has been made towards adaptive SDSs [5] and understanding multiparty conversations [6,7,8]. E.g., Siri, Cortana, Alexa, and Alisa, are typical examples of modern SDSs. Virtual assistants, e.g., Siri, Cortana, Alexa, and Alisa, are typical examples of modern SDSs Such systems face the problem of human-machine addressee detection (H-M AD) that arises in multiparty spoken conversations between several people and an Sensors 2020, 20, 2740; doi:10.3390/s20092740 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
