The objective of the course is to provide the students with a practical understanding of automatic speech processing and of the related computational tools available to achieve so. Students will learn how to implementation typical speech processing techniques of increasing complexity up to articulated tasks as speaker identification and speech recognition. The course will provide both a theoretical overview of current approaches as well as hands-on experience.
Content:
Acoustics: introduction to the properties of the speech and audio signal
Speech and audio processing: methods and tools
Automatic processing of audio/speech: automatic speech recognition and understanding, keyword spotting, speaker identification.
Open issues and challenges: privacy, low-resourced languages, computational costs
Content:
Acoustics: introduction to the properties of the speech and audio signal
Speech and audio processing: methods and tools
Automatic processing of audio/speech: automatic speech recognition and understanding, keyword spotting, speaker identification.
Open issues and challenges: privacy, low-resourced languages, computational costs
- Docente: Alessio Brutti