Speech Synthesis: Difference between revisions
Jump to navigation
Jump to search
Maria Tepei (talk | contribs) No edit summary |
|||
| Line 8: | Line 8: | ||
* [[Commerical TTS - Google, Amazon, Apple and Microsoft (2010s)]] | * [[Commerical TTS - Google, Amazon, Apple and Microsoft (2010s)]] | ||
* [[Advancements in AI TTS (2020s)]] | * [[Advancements in AI TTS (2020s)]] | ||
* [[DECtalk Speech Synthesizer (1984)]] | |||
===== New ideas ===== | ===== New ideas ===== | ||
| Line 17: | Line 18: | ||
* [[Linear Predictive Coding (1970s)]] | * [[Linear Predictive Coding (1970s)]] | ||
* [[Carnegie Mellon's FestVox Project (1984)]] | * [[Carnegie Mellon's FestVox Project (1984)]] | ||
* [[FestVox (1987)]] | * [[FestVox (1987)]] | ||
Revision as of 10:29, 18 October 2023
- Wolfgang von Kempelen's Speaking Machine (1769)
- Early attempts at mechanical synthesis: Christian Kratzenstein (1779)
- The Bell Telephone Laboratory's Voder (1930s).
- Vocoder Development (1940s)
- HMM-based speech synthesis systems (HTS) (1980s-Now)
- Festival Speech Synthesis System (1997)
- Advancements in Neural Network-Based TTS (2000s)
- Commerical TTS - Google, Amazon, Apple and Microsoft (2010s)
- Advancements in AI TTS (2020s)
- DECtalk Speech Synthesizer (1984)