Editing Advancements in AI TTS (2020s) (section)

== Historical Context ==
The history of speech synthesis can be traced back to the 18th century. The first machine that attempted to produce human speech was created by [[Mechanical synthesis|Christian Kratzenstein]] in 1769. This machine used hollow tubes to resemble resonators and by adjusting resonators’ lengths and shapes, the machine produced five vowels A, E, I, O and U. In 1791, [[Wolfgang von Kempelen's Speaking Machine (1769)|Wolfgang von Kempelen]] created a “speaking machine” that simulated the human vocal tract and could produce vowels and consonants using a series of bellows, reeds and mechanical components. Later in the 20th century, Bell Labs developed [[Voder]] (Voice Operating Demonstrator) , an electrical speech synthesizer that employed bandpass electronic filters and operator control for sound generation. 

The central concept during the early development of speech synthesis was to copy the speech<ref name=":2">Klatt, D. H. (1987). Review of text-to-speech conversion for English. ''The Journal of the Acoustical Society of America'', ''82''(3), 737–793. <nowiki>https://doi.org/10.1121/1.395275</nowiki></ref>. The approach involved either mechanical or electrical. The former aimed to mimic vocal tract movements, while the latter worked on filtering electrical signals to emulate the vocal tract's function. It is worth noting that these early machines were not text to speech systems, as they convert plain text into speech. Nevertheless, they represented significant milestones in the evolution of modern TTS systems, despite their limitations in producing a full range of sounds or sentences. [https://www.youtube.com/watch?v=0rAyrmm7vv0 A video filmed in 1939] about Voder demonstrated that the Voder could only produce a single sentence ‘she saw me’ with varying word stress. 

Full-fledged text to speech systems emerged until the late 20th century. Most of TTS systems at that time were rule-based, meaning they generated speech using predefined linguistic and phonetic rules. One of the earliest full text to speech systems MITalk<ref>Allen, J., Hunnicutt, M. S., Klatt, D. H., Armstrong, R. C., & Pisoni, D. B. (1987). ''From text to speech: The MITalk system''. Cambridge University Press.</ref>, created by researchers at the Massachusetts Institute of Technology (MIT) in 1960s, was one such rule-based system. It allowed users to hear speech as they typed. However, the speech output still lacked naturalness and expressiveness. Additionally, compiling linguistic rules for different languages requires lots of manual work and due to the flexibility of languages, it is impossible to cover all variations and exceptions.  

From late 20th onwards, new TTS techniques such as Parametric TTS, [[Hidden Markov Models in Speech Synthesis|Hidden Markov Models (HMMs)]], and Concatenative TTS were developed to address naturalness, adaptability and flexibility issues, greatly improving the performance of TTS. However, the limitations of these techniques are inevitable. For example, despite the naturalness of concatenative TTS, it lacks the ability to generate new voices because it relies heavily on recorded speech data. 

Thanks to the advancement of artificial intelligence (AI), recent TTS systems can generate natural, human-like speech by adopting innovative training and learning models, as well as enhanced traditional techniques. In the upcoming section, we will delve deeper into AI techniques.