View Proposal

---

Proposer

Matthew Aylett

Title

A GRAPHICAL USER INTERFACE FOR CONSTRUCTING AND EDITING VOCAL PUPPETRY

Goal

Create a GUI using WxPython or similar to allow editing and creation of XML puppetry input and integrate with speech synthesis

Description

Neural TTS (text to speech) systems can allow very fine specification of speech output allowing the intonation and speech rate from a source speaker to be used to guide a synthetic voice and replicate the source speakers delivery. Much spoken output generated by TTS does not need to be in real time. For example, producing audio for a speech or media performance. CereProc Ltd has developed a prototype system for taking source speech and transcription and creating XML markup to realise the same delivery in a synthetic engine. In this project a graphical user interface (GUI) will be produced to allow interactive tuning of this output. The GUI will be evaluated against a set of users and output compared to baseline TTS.

Resources

Cereproc Prototype Vocal Puppetry System

Background

Aylett, M. P., Braude, D. A., Pidcock, C. J., & Potard, B. (2019). Voice puppetry: exploring dramatic performance to develop speech synthesis. In Proc. 10th ISCA Speech Synthesis Workshop (pp. 117-120). Aylett, M. P., & Vazquez-Alvarez, Y. (2020, March). Voice puppetry: Speech synthesis adventures in human centred ai. In Proceedings of the 25th International Conference on Intelligent User Interfaces Companion (pp. 108-109). Van de Vreken, E., Richmond, K., & Lai, C. (2022, September). Voice Puppetry with FastPitch. In Interspeech 2022 (pp. 5219-5220). ISCA.

Url

Difficulty Level

Challenging

Ethical Approval

InterfaceOnly

Number Of Students

2

Supervisor

Matthew Aylett

Keywords

speech technology, hci, gui programming

Degrees

Bachelor of Science in Computer Science
Master of Engineering in Software Engineering
Master of Design in Games Design and Development
Master of Science in Artificial Intelligence
Master of Science in Human Robot Interaction