Sensory Releases Speech Recognition Models for Children

October 6 2021, 00:50
Sensory, the recognized voice recognition and edge-AI voice solutions specialist announced availability of new custom trained speech recognition models that understand the unique linguistic patterns associated with children’s speech. This new children’s speech recognizer unlocks a higher level of accuracy and privacy for apps, toys, kid’s wearables, and education technologies, all key market segments for voice interface applications that Sensory is targeting.
 

The new recognizer designed for kids’ voices, supports both Sensory’s TrulyHandsfree phrase spotting technology and TrulyNatural large vocabulary continuous speech recognizer. As the company reinforces, with this technology advancement, developers of apps, children’s toys, kid’s wearables, and education technology can implement voice control technology with unparalleled accuracy and privacy due to Sensory’s AI-on-the-edge architecture.

Accurately recognizing children’s speech is challenging because it differs from adult speech in many ways. A scarcity of available training data makes this problem even more difficult to solve. Over many years Sensory collected and analyzed significant amounts of children’s speech to better understand and model the specifics of how children talk. Initial testing on a corpus of spontaneous kid’s speech, reveals up to a 33% reduction in word error rate, when compared to an adult speech recognition model.

“Sensory has some of most talented technologists in the speech industry,” states Todd Mozer, CEO at Sensory. “We challenged the team to create a private and accurate recognizer for kid’s speech and they delivered. This opens up new and fun voice enabled products for kids of all ages.”

Generalplus Technology, headquartered in Taiwan, is a worldwide supplier of integrated circuits for speech and toys. They have shipped millions of products with voice control. “Sensory’s new kid’s speech recognition has already been integrated into several of our ICs and we are seeing strong interest from our customers,” says Jacky Chen, marketing manager at Generalplus.

Developers can now access child speech models, as well as Sensory’s industry-leading adult speech models, within Sensory’s VoiceHub developer portal. The flexibility of VoiceHub enables direct export to many supported DSP and microcontroller formats, including the newly added Generalplus ICs.

Sensory’s technologies are already widely deployed in consumer electronics applications including mobile phones, automotive, wearables, toys, IoT, PC’s, medical products and various home electronics. Sensory’s product line includes TrulyHandsfree voice control, TrulySecure biometric authentication, and TrulyNatural large vocabulary natural language embedded speech recognition.
www.sensory.com
 
related items