Category Archives: Uncategorized

Spectral Synthesis Revisited

I haven’t had a chance to get much coding done over the last couple months. However, I’ve been doing a lot of reading on various vocal synthesis technologies. I’d read quite a bit about spectral modeling synthesis (SMS) before, and … Continue reading

Posted in Uncategorized | Tagged , , | 2 Comments

Articulation

One of the goals of synSinger is clear articulation. I’d always assumed that interpolating formant transitions with non-linear curves would give better results than simple linear interpolation. But while the results may be more “natural”, the aren’t as clear and … Continue reading

Posted in Uncategorized | Leave a comment

Silent Letter

For a while, the pop group America had a pattern of starting the names of their albums with the letter “H”… a “silent letter.” However, the /H/ in synSinger turned out to be less than silent. The phoneme /H/ is … Continue reading

Posted in Uncategorized | Tagged , , | Leave a comment

Amplitude of Voicing Envelopes

One of the problems with synSinger has been transitions silence and voiced phonemes. Earlier versions had all the parameters transition during the transition time. But since the voicing transition is often shorter than the formant transition time, this led to … Continue reading

Posted in Uncategorized | Tagged , , , | Leave a comment

Singing Again

With most of the phonemes in place, I was able to get synSinger “talk” through “Twinkle, Twinkle, Little Star” in monotone. That meant the next thing to do was add support for singing pitches. I was able to re-use a … Continue reading

Posted in Uncategorized | Leave a comment

Working on Consonants

I’ve got most of the vowels working reasonably well, so I’ve started working on the voice consonants, starting with the voiced plosives /B, D, G/. I cheated and only worked on the initial versions (i.e. /D EY/ rather than /EH … Continue reading

Posted in Uncategorized | Leave a comment

One more time!

I’ve begun rewriting synSinger yet again. Many of the core routines are going to (mostly) be able to stay in place – for example, the core synthesis routines, and the MusicXML parser. Following the maxim “Premature optimization is the root … Continue reading

Posted in Uncategorized | 8 Comments