I continue my conversation with Dr, Sue Hertz, digging deeper into the complexities of text-to-speech technology, including the challenges of embedding emotions into speech. We talk about specific examples of speech nuance - like the difference in the sound of the letter “p” in the word “Poke” versus “Spoke”. We also discuss how it has taken years of research to get to the point where Synfonica’s text-to-speech system is today.  I loved hearing her talk about her fascination with how listeners parse the nuances of speech. 

Ver todos los episodios