News for hackers. Stuff that matters.
Re:Voc: a physical model of the vocal tract, written in ANSI C by vortico on Monday June 12, 2017 @08:57PM (#14542272)
Yes, speech recognition and speech generation would be easier to implement if you used neural networks that were trained on these vocal cord inputs rather than audio samples. In either case, you'd need to solve the inverse problem to generate vocal cord parameters given an audio sample. This seems difficult but I'd imagine some commercial software packages do it to some extent.
Re:Voc: a physical model of the vocal tract, written in ANSI C by smaddox on Monday June 12, 2017 @09:50PM (#14542419)
Or you could let the neural network solve the inverse problem for you, at least for speech generation.
Re:Voc: a physical model of the vocal tract, written in ANSI C by skykooler on Tuesday June 13, 2017 @12:57AM (#14542929)
I would imagine a neural network that fed parameter values to Voc would be far faster (real-time?) than something like WaveNet which needs to sample the output thousands of times a second.
Re:Voc: a physical model of the vocal tract, written in ANSI C by zebproj on Tuesday June 13, 2017 @01:03AM (#14542944)
Correct. WaveNet is a very brute force approach to speech synthesis.