Sensory fast-tracks accurate custom voice UIs using ChatGPT generative AI
U.S.-based software company Sensory has updated its VoiceHub online portal to include new generative AI (artificial intelligence) features.
According to the firm, VoiceHub 2.0 makes it easier for developers to build custom voice user interfaces (UIs) that can comprehend spoken commands and natural language.
“Speech recognition is important in many applications, but not all needs are the same,” explains Sensory CEO Todd Mozer.
The executive adds that Sensory’s scalable development tools were designed to offer developers a comprehensive platform for creating various types of applications, including compact embedded models for detecting wake words and commands, as well as advanced Natural Language Understanding (NLU) voice UIs with extensive features.
(VoiceHub 2.0’s new project tab. Credit: 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,” Mozer says.
From a technical standpoint, VoiceHub 2.0 relies on ChatGPT’s capabilities to enable a new “Task Explorer” feature that streamlines the creation of large vocabulary or natural language (TrulyNatural-based) voice UIs.
Task Explorer’s generative AI swiftly generates intents, commands, and relevant slots for projects by entering the domain type. Users can select applicable options to match their product’s capabilities, and the program suggests phrases to accelerate voice user interface development based on the domain or product category.
VoiceHub 2.0’s phrase suggestions. Credit: Sensory.
Beyond its AI capabilities, VoiceHub 2.0 also features a refreshed portal UI layout and supports 25 languages and regional dialects. The VoiceHub mobile apps for iOS and Android have also been updated to maintain compatibility.
The new features come almost a year after Sensory and STMicroelectronics announced a new collaboration.
Article Topics
ChatGPT | generative AI | research and development | Sensory | speech recognition | voice biometrics
Comments