ESpeak-ng: speech synthesizer with more than one hundred languages and accents

Re:ESpeak-ng: speech synthesizer with more than one hundred ... by miki123211 on Thursday May 02, 2024 @01:47AM (#40233078)

You probably could by what I call the "eastern-european method." Record one wave period of each phoneme, perhaps two for plosives, downsample to 8 or 11 kHz 8 bit, and repeat that recording on-the-fly enough times to make the right sound. If you're thinking "mod file", you're on the right track.

For phonetically simple languages, such a system can easily fit on a microcontroller with kilobytes of RAM and a slow CPU. English might require a little bit more on the text-to-phoneme stage, but you can definitely go far below 1MB.

[ Parent | on HN ]

Re:ESpeak-ng: speech synthesizer with more than one hundred ... by rhdunn on Thursday May 02, 2024 @04:05AM (#40233819)

That's effectively what eSpeak-ng is doing.

For the CMU flite voices they represent the data as LPC (linear predictive coding) data with residual remainder (residual excited LPC). The HTS models use simple neural networks to predict the waveforms -- IIRC, these are similar to RNNs.

The MBROLA models use OLA (overlapped add) to overlap small waveform samples. They also use diphone samples taken from midpoint to midpoint in order to create better phoneme transitions.

[ Parent | on HN ]