The Voder: 1939, the worlds first electronic voice synthesizer

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

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

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 given the underlying audio information? Also note that NPSS has some amount of post-processing, at least reverb and perhaps other common musical mixing - we don't really know how these samples are generated, and I have a hard time decyphering exactly what inputs are required, and what are generated from the paper alone. However, I really, really, really like NPSS - I just don't think the comparison you are making is valid here. These features (f0, duration, pronunciation) are some of the most difficult things to learn to model from datasets of speech and text directly, and I am not sure how they got the subset used (I think only f0 and pronunciation/phoneme) for this NPSS model. Giving creators fine-grained control of the performance (as in NPSS) is quite cool, and if these systems can get fas