NVIDIA Corp has launched new research and tools to capture natural speech qualities by letting one train the AI system with one's voice, TechCrunch reports based on the Interspeech 2021 Conference.
The features could give Amazon’.com Inc's (NASDAQ: AMZN) Alexa, Alphabet Inc's (NASDAQ: GOOG) (NASDAQ: GOOGL) Google Assistant, and other AI assistants a run for their money.
NVIDIA's text-to-speech research team has developed a RAD-TTS model that allows training a text-to-speech model with their voice, including the pacing, tonality, timbre, and more. RAD-TTS' voice conversion feature lets a user deliver one speaker's words using another person's voice.
NVIDIA will distribute some of this optimized research running efficiently on NVIDIA GPUs. Developers can fine-tune any model for their use cases, speeding up training using mixed-precision computing on NVIDIA Tensor Core GPUs.
Price Action: NVDA shares closed lower by 1.32% at $223.85 on the last check Tuesday.