Amazon Announces One Billion Parameter Speech Model BASE TTS

Amazon Science recently published their work on Big Adaptive Streamable TTS with Emergent abilities (BASE TTS). BASE TTS supports voice-cloning and outperforms baseline TTS models when evaluated by human judges. Further, Amazon's experiments show that scaling model and data size improves the subjective quality of the model's output.

ai amazon anthony base tts big billion cloning data deep learning human judges ml & data engineering natural language processing neural networks quality scaling science show speech tts voice work