お客様の素早い設計とより早い製品化を実現する、技術情報と専門知識をご紹介します。
Sign in to access this content and additional site features.
This demonstration features Text-to-Speech (TTS) on the i.MX RT700 microcontroller unit (MCU) and the i.MX 8M and i.MX 9 microprocessing unit (MPU) families. This speech synthesis enables AI assistants and enhances user experiences. For MPUs, the TTS model is based on variational Inference with adversarial learning for end-to-end Text-to-Speech (VITS) architecture. TTS can process multiple voices including different accents, registers and genders depending on the language. The frequency sampling rate is 16 kHz or 22 kHz, depending on the model. With the i.MX RT700 MCU, the TTS performance is neural processing unit (NPU)-driven.
Explore NXP's voice processing solutions for consumer and industrial applications.