From Hal to Siri: How Computers Learned to Speak
New Books in Science, Technology, and Society
00:00
The Evolution of Computer Speech Synthesis
This chapter examines the challenges and advancements in early computer music and speech synthesis, particularly during the 1960s. It highlights the limitations of technology in achieving natural-sounding voices and the transition from rule-based systems to more advanced methods like diphone synthesis and neural networks. The discussion underscores the importance of balancing structure with the spontaneity of spoken language in the evolution of synthetic speech.
Transcript
Play full episode
