AI can be used for much more than just transforming synthesized speech from robocalls and GPS navigation systems into the virtual assistants in smartphones and smart speakers of today. How so? There’s still a large gap to fill in AI-synthesized speech and the human speech we hear in daily conversation due to the complex rhythms, intonation and timbre. NVIDIA researchers are currently building models and tools for high-quality, controllable speech synthesis that capture the granule details of human speech, without audio artifacts.
The models they are building can assist voice automated customer service lines for banks / retailers, bring video-game characters to life, or just provide real-time speech synthesis for personalized digital avatars. NVIDIA’s very own in-house creative team even used this expressive speech synthesis technology to produce expressive narration for a video series on the power of AI.
- Fueled by the revolutionary AMD Ryzen 5000 H-Series mobile processor, this IdeaPad gaming laptop delivers the wins. With 6 ultra-responsive cores,...
- 15.6" FHD (1920 x 1080) IPS display with NVIDIA GeForce GTX 1650 GPU to supercharge your favorite games. Slingshot your gaming visuals with 120Hz...
- 8GB 3200 MHz DDR4 RAM memory and 256GB M.2 PCIe SSD storage
The AI model’s capabilities go beyond voiceover work: text-to-speech can be used in gaming, to aid individuals with vocal disabilities or to help users translate between languages in their own voice. It can even recreate the performances of iconic singers, matching not only the melody of a song, but also the emotional expression behind the vocals,” said NVIDIA.
