The Language Project Podcast

From ‘Cot’ vs ‘Caught’ to Pioneering Technologies: Interview with Dr. Sue Hertz

November 15, 2022 Jay Mason Episode 21
From ‘Cot’ vs ‘Caught’ to Pioneering Technologies: Interview with Dr. Sue Hertz
The Language Project Podcast
More Info
The Language Project Podcast
From ‘Cot’ vs ‘Caught’ to Pioneering Technologies: Interview with Dr. Sue Hertz
Nov 15, 2022 Episode 21
Jay Mason

Come join me as I speak with Dr. Sue Hertz, Adjunct Professor at Cornell University and President of Synfonica LLC, a speech technology company developing knowledge-based text-to-speech systems and related applications. She shares what initially sparked her interest in linguistics and how learning computer programming became an essential part of her journey. We’ll learn about her pioneering research and development in text-to-speech synthesis over the last several decades. I was especially inspired to hear about how one of her systems is still one of the most widely used programs in screen readers for blind individuals.  

Dr. Hertz asked me to clarify that when she said that the knowledge-based approach Synfonica is taking to text-to-speech synthesis differs from the approaches taken by others, she meant “others today.” Decades ago, there was no choice but to use such an approach due to the severe memory limitations of computer systems at that time. 

Show Notes

Come join me as I speak with Dr. Sue Hertz, Adjunct Professor at Cornell University and President of Synfonica LLC, a speech technology company developing knowledge-based text-to-speech systems and related applications. She shares what initially sparked her interest in linguistics and how learning computer programming became an essential part of her journey. We’ll learn about her pioneering research and development in text-to-speech synthesis over the last several decades. I was especially inspired to hear about how one of her systems is still one of the most widely used programs in screen readers for blind individuals.  

Dr. Hertz asked me to clarify that when she said that the knowledge-based approach Synfonica is taking to text-to-speech synthesis differs from the approaches taken by others, she meant “others today.” Decades ago, there was no choice but to use such an approach due to the severe memory limitations of computer systems at that time.