The Californer - "Sensory VoiceHub 2.0: Rapid Custom Voice UI Dev & Prototyping with Generative AI"

Trending...

VoiceHub now supports more hardware platforms, more languages and dialects, and features an updated portal UI for faster and easier prototyping

SANTA CLARA, Calif. - Californer -- Sensory, a leading provider of AI-based speech recognition technologies, announces the launch of VoiceHub 2.0. The new and improved version of Sensory's popular web portal integrates generative AI-powered tools, making it an even more powerful, flexible and time-saving platform for developers to create custom voice UIs capable of understanding spoken commands and natural language.

"Speech recognition is important in many applications, but not all needs are the same. Our scalable VoiceHub voice UI development tools were created to provide developers a one-stop-shop for applications ranging from ultra-small footprint embedded wake words and command models to full-featured NLU voice UIs," said Todd Mozer, CEO of Sensory. "With VoiceHub 2.0, we're providing an even more powerful, flexible, and intuitive tool that harnesses the power of generative AI to make short work of creating high-performance speech recognition models."

Since its launch, VoiceHub has helped numerous engineers develop high-performance wake words, voice control command sets, and grammar-based language models with flexible intents and entities. Most companies use these models for demos and product development, but some customers have recently used VoiceHub models in real world products, a testament to the high-performance and overall quality of experience. With the new updates to the user interface, more platform integrations, numerous language and regional dialects, and access to the latest versions of TrulyHandsfree and TrulyNatural, VoiceHub changes the game by providing all the tools needed to develop high-functioning embedded voice UIs with unrivaled accuracy.

More on The Californer

Generative AI Integration

VoiceHub 2.0 integrates ChatGPT (https://www.youtube.com/watch?v=do5BW8BBJUA)'s vast capabilities to enable a new "Task Explorer" feature that streamlines the creation of large vocabulary or natural language (TrulyNatural-based) voice UIs. By simply entering the domain type of the project, Task Explorer's generative AI quickly provides a variety of intents or commands, and relevant slots or categories for the project type via an interactive mapping tool or within the language model builder. Users would simply select all options that would be relevant to their product's/project's capabilities and features. Based on domain or product category, VoiceHub's new Task Explorer feature can also generate a list of suggested phrases for the language model, which users can pick from to expedite voice user interface development.

A Fresh New Portal UX

Beyond the many added features and benefits, VoiceHub 2.0 also received a facelift (https://www.youtube.com/watch?v=dOj7KQC-qvw), boasting a refreshed portal UI layout, and new features that allow for sharing and importing of projects in an easy-to-use drag and drop format. The VoiceHub mobile app for iOS and Android has also been updated to maintain compatibility.

Foundational Tech Updates

TrulyHandsfree Micro 7.1.0 has been updated with speed improvements, and now supports even more hardware platforms, including ARM Cortex-M4, Silicon Labs Cortex-M33/M, Ambiq Apollo 4, Cadence Hifi5, Qualcomm, and Xmos xcore.ai. TrulyHandsfree supports Android, iOS, Linux and Windows operating systems - support for other operating systems can be added upon request.

More on The Californer

TrulyNatural 6.21.0 features a background model for US English that improves out-of-vocabulary rejection, making it even easier for grammars created in VoiceHub to perform with high accuracy in real world applications. The TrulyNatural SDK 6.21.0 now requires less RAM for recognizers on small, embedded platforms and adds Voice Activity Detectors for the SNSR-lite Large Vocabulary Continuous Speech Recognizer. In other words, VoiceHub generated grammars using this new version of TNL may be used on a wider range of devices and can run smaller with great performance on the STM32 chip. Additionally, VoiceHub's TrulyNatural tools will include statistical language models, further improving flexibility and natural language accuracy.

Robust Language Support

VoiceHub 2.0 now supports 25 languages and regional dialects, including Arabic, German, English (Australia, India, UK, USA, USA kids), Spanish, French, Italian, Japanese, Korean, Polish, Portuguese, Russian, Swedish, and Mandarin (Universal, Mainland, Taiwanese). Access to these languages allows developers the flexibility to create voice UI solutions for products with global reach.

VoiceHub 2.0 is available now. To learn more or to try it out for yourself, visit www.sensory.com/voicehub.