– SensiML Data Studio democratizes speech recognition on small devices with new text-to-speech synthesis dataset generation capabilities.
PORTLAND, Ore., July 25, 2024 /PRNewswire/ — SensiML™ Corporation, a leader in AI software for IoT and a subsidiary of QuickLogic (NASDAQ: QUIK), today announced new generative AI capabilities enhancing Data Studio, a dataset management application for IoT edge devices. This innovative new feature enables embedded device developers to leverage text-to-speech (TTS) and AI voice generation to rapidly create ultra-realistic synthetic speech datasets essential for building robust keyword recognition, voice command and speaker identification models. Using these rapidly generated speech datasets, developers can now easily create speech recognition AI models using SensiML’s AutoML development tools. These models are specifically optimized to run autonomously and efficiently on low-power microcontrollers used in edge IoT applications.
SensiML Data Studio democratizes speech recognition on small devices with new text-to-speech synthetic dataset generation capabilities.
SensiML’s new features leverage ElevenLabs’ cutting-edge speech generation technology to simplify the creation of large-scale, high-quality datasets. Developers can now generate synthetic speech data with unparalleled realism and customized voice attributes, such as pitch, rhythm and tone, to meet specific application requirements. This eliminates the time-consuming and costly process of manually recording phrases from a large, diverse population of speakers, accelerating time to market for voice-enabled IoT devices.
Designed for ease of use, the new TTS and AI speech generation capabilities seamlessly integrate into your existing Data Studio workflow.
Key benefits of SensiML generative AI enhancements include:
High-quality speech output: Generates natural, expressive speech samples to improve user experience. Versatile: Supports a wide range of languages and dialects to serve diverse global markets. Efficient: Streamlines the process of integrating speech generation into AI models to reduce time to market. Scalable: Suitable for applications of any scale, from small IoT devices to large-scale deployments.
“By bringing this generative AI capability to our Data Studio application, SensiML continues to push the boundaries of what’s possible with AI for IoT,” said Chris Rogers, CEO of SensiML. “Developers can now leverage cutting-edge synthetic speech technology to create highly accurate and diverse training datasets, accelerating the deployment of intelligent voice-controlled applications directly on microcontrollers.”
The created datasets are seamlessly compatible with SensiML’s Analytics Studio and Piccolo AI™, an open-source AutoML tool, enabling a smooth transition from dataset creation to model deployment.
Real-world example:
Consider a smart home security system that uses voice commands for activation and status updates. SensiML’s new text-to-speech and AI voice generation capabilities enable developers to efficiently create extensive voice datasets, enabling the system to accurately recognize a wide range of user commands. This advancement accelerates the development and deployment of systems, allowing homeowners to benefit from advanced, reliable, and responsive security solutions without the need for a constant internet connection.
This capability greatly enhances the ability for developers to custom build their own ML code for IoT devices that need to process complex speech and sound recognition tasks directly on-device, without the need for constant connectivity or heavy computational power. This is especially useful for applications in environments where connectivity may be unreliable and fast, reliable processing is essential.
About SensiML
SensiML, a QuickLogic (NASDAQ: QUIK) company, provides cutting-edge software enabling ultra-low power IoT endpoints that implement AI to transform raw sensor data into meaningful insights on the device itself. The company’s flagship solution, the SensiML Analytics Toolkit, provides an end-to-end development platform spanning data collection, labeling, auto-generation of algorithms and firmware, and testing. The SensiML Toolkit supports a growing range of hardware including Microchip® 8/16/32-bit MCUs, Arm® Cortex®-M class and above microcontroller cores, Intel® x86 instruction set processors, and heterogeneous-core AI/ML optimized SoCs. For more information, please visit https://sensiml.com.
SensiML and logos are trademarks of SensiML. All other trademarks are the property of their respective owners and should be treated as such.
SOURCE SensiML Corporation
