5 papers
Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation
Dominika Woszczyk, Andreas Triantafyllopoulos, Jura Miniota +2
Text-to-speech (TTS) evaluation is an open challenge. While the primary target was "naturalness," recent fidelity gains shifted focus toward "appropriateness" and whether speech is…
Understanding Dementia Speech Alignment with Diffusion-Based Image Generation
Mansi, Anastasios Lepipas, Dominika Woszczyk +2
Text-to-image models generate highly realistic images based on natural language descriptions and millions of users use them to create and share images online. While it is expected…
Voice Conversion for Lombard Speaking Style with Implicit and Explicit Acoustic Feature Conditioning
Dominika Woszczyk, Manuel Sam Ribeiro, Thomas Merritt +1
Text-to-Speech (TTS) systems in Lombard speaking style can improve the overall intelligibility of speech, useful for hearing loss and noisy conditions. However, training those mode…
ClaritySpeech: Dementia Obfuscation in Speech
Dominika Woszczyk, Ranya Aloufi, Soteris Demetriou
Dementia, a neurodegenerative disease, alters speech patterns, creating communication barriers and raising privacy concerns. Current speech technologies, such as automatic speech t…
DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech
Dominika Woszczyk, Soteris Demetriou
Dementia is a sensitive neurocognitive disorder affecting tens of millions of people worldwide and its cases are expected to triple by 2050. Alarmingly, recent advancements in deme…