The department of Voice and Sound Technology conducts basic and applied research in the fields of Speech and Music signal processing. The department’s research and development activities focuses on the areas of Text-to-Speech synthesis (TTS), automatic speech recognition (ASR), speaker indexing and speech diarization, speech signal quality evaluation, analysis, processing and modeling of speech and music signals, speech compression and coding and spectral analysis. Furthermore, the department has expertise in issues of accessibility, assistive technologies and design-for-all, as they relate to the aforementioned technologies, with the goal of adopting them in contemporary platforms as well as the web.
Further to the above, the department’s aim is to design and develop core technologies and prototypes with the intent of exploiting them in innovative applications and services, as well as to develop resources and tools in the above fields. The department actively participates in National and European research and development projects.
Development platforms, systems as well as tools are developed for:
- Text-to-Speech synthesis
- Automatic speech recognition
- Speaker indexing
- Speech-enabled web content
- Spectral analysis
- Speech enhancement and denoising
- Greeklish to Greek transliteration