ESR14 : Gender and vocal alignment in speakers and robots

PhD fellowship: Carol Figueroa

Hello, my name is Carol Figueroa and I am originally from California. I’ve always had an interest in language and mathematics. I received my Bachelor degrees in Linguistics and Computer Science from the University of California, Santa Cruz. I then went on to complete my MSc in Speech and Language Processing from the University of Edinburgh. It was during the MSc program that I learned about the different fields of language technology such as text-to-speech, automatic speech recognition, and natural language processing.

I am excited to be part of COBRA and to be part of this project where all these language technologies are used for the social robot Furhat. 

Objectives:

ESR14 will focus on acoustic-prosodic alignment at the discourse level. In addition to playing a crucial role in speakers’ joint understanding of what they are talking about, vocal alignment may also have an important social dimension. Thus, previous work reveals that vocal alignment tends to occur to a greater extent in women than in men. Recent studies on human-robot interactions, however, suggest that there is a tendency for both women and men to disalign with respect to the robot’s voice, regardless of the robot’s voice gender. This may be attributable to the fact that humans do not treat robots’ voices as human voices or, alternatively, because of the robots’ current limited capacities to align themselves with human voices. The goal of ESR14’s project will be to provide a fuller characterization of acoustic-prosodic in humans and robots with a focus on gender and the communicative situation.

Applicants should have a Master’s degree in a subject relevant for the research, such as computer science, language technology, or cognitive science. Applicants are expected to have good skills in programming and experience in machine learning. Some experience in linguistics is considered an advantage. 


Expected results:

  • Better understanding of the social function of vocal alignment;
  • New techniques for adapting a spoken dialogue management system to the user’s gender characteristics.

Based in Stockholm, Sweden

Full-time three-year contract, starting September 2020

PhD enrolment at: Aix-Marseille University, France

Main supervisors’ institutions: Furhat Robotics, Stockholm, Sweden, and Aix-Marseille University, France

Main supervisors: Prof Gabriel Skantze and Dr Magalie Ochs

Secondments:

  • Aix-Marseille University: training in designing naturalistic gender-based and situation specific speech elicitation techniques (5,5 months);
  • IISAS, Bratislava: training in fine-grained acoustic-prosodic alignment informed by dialogue progression (5 months).

Co-supervisor’s institution:

  • IISAS, Bratislava, Slovakia
Scroll to top