The Voder: 1939, the worlds first electronic voice synthesizer
Why Hacker News recommends it
HN cites it as a historic demonstration of early speech synthesis, including discussions about whether the demo was genuine.
What it is
A short look at the Voder, the first electronic voice synthesizer, demonstrated by Bell Labs at the 1939 World's Fair. It was operated by trained women using ten finger keys, foot pedals and a knee lever.
Recommended by 0 HN commenters across 0 different months, 2017 to 2024.
What Hacker News said
Cites kastnerkyle · 2017-04 · on “Lyrebird – An API to copy the voice of anyone”
This model is quite cool, but also quite a bit different than what lyrebird.ai is doing. NPSS has a lot of extra information in the control inputs about pronunciation and timing (the part-of-phoneme timer feature) - this means that most of the "hard parts" (in my opinion) for naturalness are control inputs to NPSS/WaveNet style models, rather than variables the model must generate globally and consistently as in lyrebird. At generation time NPSS appears to generate each component autoregressively as well, but I am not clear on whether the demo samples do this or if they use "true" values for f0 at least - what forces the model to sing the exact same melody, if many melodies are possible give
Cites JKCalhoun · 2023-07 · on “Voder Speech Synthesizer”
I was skeptical that you could even type an intelligible phonetic "She saw me" with only two phonemes let alone give it the rise and fall demonstrated. I've played with the SP0256 speech synthesis IC and found constructing intelligible words challenging even with all the phonemes available on that silicon. This extended video has me thinking it probably was legit though: [this video]
Cites sargstuff · 2024-01 · on “An Approach to Sound Synthesis with L-Systems”
Vocoder more representative of the ADSR approach.[0] Although adding the orchestral music score single track equivalent of speech production looks about the same.[1] Space / technical complexity not withstanding, could generate a full choir & full orchestra with 1 vocoder per singer/ 1 vocoder per orchestra instrument. Suppose chatgpt could assist with reducing/minimizing amount of vocoders needed via waveform overlap reductions at the expense of being specific for given set of song(s). ---- [0] : [this video] [1] : [LINK]