SensiML, a subsidiary of QuickLogic, has unveiled a new generative AI feature to enhance its Data Studio application, used for dataset management in IoT Edge devices.
This capability enables embedded device developers to leverage text-to-speech (TTS) and AI voice generation to create hyper-realistic synthetic speech datasets. These datasets are crucial for building robust models for keyword recognition, voice command, and speaker identification. Using these speech datasets, developers can now easily create speech recognition AI models with SensiML’s AutoML development tools, optimised for autonomous and efficient operation on low-power microcontrollers used in Edge IoT applications.
By integrating advanced speech generation technology from ElevenLabs, SensiML’s new feature simplifies the creation of large, high-quality datasets. Developers can generate synthetic speech data with exceptional realism and tailor voice attributes such as pitch, cadence, and tone to meet specific application requirements. This eliminates the laborious and costly process of manually recording phrases from diverse speakers, accelerating the time-to-market for voice-enabled IoT devices.
The new TTS and AI voice generation feature is designed for user-friendliness and seamless integration into existing Data Studio workflows.
Key benefits of SensiML’s generative AI enhancement include:
- High-quality voice output: Produces natural and expressive voice samples, enhancing user experiences
- Versatility: Supports a wide range of languages and dialects, catering to diverse global markets
- Efficiency: Streamlines the process of integrating voice generation into AI models, reducing time-to-market
- Scalability: Suitable for applications of all sizes, from small IoT devices to large-scale deployments
“With the introduction of this generative AI feature into our Data Studio application, SensiML continues to push the boundaries of what’s possible in AI for IoT,” explained Chris Rogers, CEO of SensiML. “Developers can now harness state-of-the-art synthetic speech technology to create highly accurate and diverse training datasets, accelerating the deployment of intelligent voice-controlled applications directly on microcontrollers.”
The generated datasets are fully compatible with SensiML’s Analytics Studio and its open-source AutoML tool, Piccolo AI, ensuring a smooth transition from dataset creation to model deployment.
As an example, consider a smart home security system that uses voice commands for activation and status updates. With SensiML’s new text-to-speech and AI voice generation feature, developers can efficiently create extensive voice datasets, enabling the system to accurately recognise a wide range of user commands. This advancement speeds up the development and deployment of the system, providing homeowners with an advanced, reliable, and responsive security solution without requiring constant internet connectivity.
This feature marks a significant development, empowering developers to custom build their own machine learning code for IoT devices needing to handle complex voice and sound recognition tasks directly on-device, without the need for constant connectivity or high computational power. It is particularly beneficial for applications in environments where connectivity may be inconsistent, and where fast, reliable processing is crucial.
There’s plenty of other editorial on our sister site, Electronic Specifier! Or you can always join in the conversation by commenting below or visiting our LinkedIn page.