Speech Synthesis and Voice Conversion: Machine Learning Can Mimic Anyone's Voice

Explore the cutting-edge field of voice conversion and speech synthesis in this 57-minute lecture by Dr. Berrak Sisman from the University of Texas at Dallas. Delve into the fascinating world of artificial intelligence that enables the transformation of one person's voice into another's while preserving linguistic content. Discover the latest advancements in voice conversion techniques, including speech analysis, spectral conversion, prosody conversion, speaker characterization, and vocoding. Learn about the current capabilities of producing human-like voice quality with high speaker similarity, and examine the promises and limitations of these technologies. Gain insights into available resources for expressive voice conversion research and understand the broader implications of these developments in the field of speech processing.