Anton Ragni

Dr. Anton Ragni is a Senior Lecturer in Speech and Language Technologies at the University of Sheffield's School of Computer Science, where he serves as Assessments Lead and contributes to the Speech and Hearing (SpandH) research group.

His educational background includes:

• BEng in Information Technology from the University of Tartu (2005)
• MEng in Information Technology from the University of Tartu (2007)
• PhD from the University of Cambridge (2013)

Ragni's research centers on machine learning approaches for speech and language processing, with core expertise in automatic speech recognition (ASR), expressive speech synthesis, spoken language translation, information retrieval, and conversation modeling. His work increasingly integrates self-supervised learning and foundation models to address challenges in speech technology and cross-domain applications like music processing.

Analysis of his recent publications reveals a strong trend toward applying speech processing techniques to music understanding and developing robust ASR systems for specialized populations, including hearing-impaired users and children. His work demonstrates consistent innovation in leveraging contextual information and novel architectures like energy-based models.

His scientific recognition includes:

• Best Student Paper Award at IEEE ASRU 2011 for 'Generative kernels for noise robust ASR'

Ragni has secured significant research funding as Principal Investigator and Co-Principal Investigator:

• EPSRC grant 'Exemplar-based Expressive Speech Synthesis' (2021-2023, £218,290) as PI
• Innovate UK grant 'Automatic voice conversion for transforming professional adult voice actors to artificial child voice actors' (2021-2023, £173,605) as Co-PI

He actively contributes to the Speech and Hearing research group, focusing on advancing speech technology through interdisciplinary collaboration and real-world applications.