NVIDIA Riva Studio uses AI to clone your voice and it requires only 30 minutes of audio recordings without requiring any code. Technically speaking, this framework combines forward-sum algorithm, the Viterbi algorithm, and a simple and efficient static prior.
The researchers found that their alignment learning framework improved all tested TTS architectures, including both autoregressive (Flowtron, Tacotron 2) and non-autoregressive (FastPitch, FastSpeech 2, RAD-TTS). More specifically, it not only improved the alignment convergence speed of existing attention-based mechanisms, but also simplified the training pipeline, thus making the models more robust to errors on long utterances. Plus, it’s also evident that the framework improved the perceived speech synthesis quality. Want to try it out yourself? NVIDIA Riva Studio early access signup can be found here, although a mutual NDA is needed before granting access.
- Powerful Productivity: 11th Generation Intel Core i3-1115G4 Dual Core processor delivers unmatched speed and intelligence, enabling impressive...
- Visibly Stunning: Experience sharp details and crisp colors on the 15.6" Full HD IPS display with 82.58% screen-to-body, 16:9 aspect ratio and narrow...
- Ergonomic Typing: Ergonomically-designed hinge lifts the keyboard for comfortable typing, improved cooling, and a better sound experience
