Conexant AudioSmart Provides Superior Far-Field Speech Recognition Performance on First Smart Speaker for Korean Market
SK Telecom works with Conexant to produce first smart speaker capable of natural language processing of Korean language; Enables device to hear users accurately from a distance and in noise
IRVINE, Calif., Oct. 12, 2016 -- Conexant Systems, Inc., a leading provider of audio and voice technology solutions that enable a more natural user experience, today announced that SK Telecom, Korea's largest mobile carrier, is implementing AudioSmart™ far-field voice solutions to help the new NUGU™ smart speaker hear users' requests accurately from a considerable distance away from the device. Conexant provides advanced voice processing technologies that help NUGU voice services offer the highest voice recognition accuracy rate in Korea. Conexant AudioSmart technology enables highly accurate voice control in smart home applications, robots, IoT devices, and more.
"When developing the NUGU personal digital assistant, our engineers focused heavily on ensuring it would provide an optimal voice-enabled user experience," said Myung Soon Park, Senior Vice President, Future Technology R&D Center at SK Telecom. "When choosing a technology partner to help us achieve the level of speech recognition accuracy we wanted, Conexant was an obvious choice. Their technology allows our NUGU personal digital assistant to overcome distance and noise related challenges and offer ideal near- and far-field speech recognition performance, as well as enables users to interrupt and interact with the device when it's playing media."
Enabling speech recognition and voice control from a distance in smart platforms requires overcoming substantial challenges related to echo cancellation, background noise, microphone speaker position and more. Conexant solutions are able to separate voice commands from background noise so that the speech recognition engine hears the user's command as clearly as possible, which in turn provides a far more accurate voice-enabled experience, even in noisy, real-world conditions, up to several meters away from the target device. The Conexant Far-Field Voice Input Processor solution for voice interactive devices is an industry first. This family of processors leverages Conexant AudioSmart™ far-field voice processing algorithms, enabling OEMs to deliver products, like NUGU, that offer a voice-enabled user experience.
"As the voice-enabled revolution continues to shift the way people interact with devices of all types, reliance on speech enhancement technologies that help devices hear user commands more accurately will continue to grow," said Saleel Awsare, President of Conexant. "Conexant has been a leading provider of voice processing solutions that improve speech recognition accuracy and enable advanced voice capabilities for years. We are pleased to be working with SKT to bolster the speech recognition performance of their NUGU smart speaker."
To learn more, please visit www.conexant.com, follow them on LinkedIn, like them on Facebook, and view their videos on YouTube.
Conexant Systems, Inc. is the CE industry's go-to source for hardware and software solutions that offer unrivaled performance for audio and voice applications. The company combines its significant IP portfolio in DSP, analog and mixed signal technology with embedded software to enrich and expand audio and voice capabilities of products across nearly every vertical of the CE space. Founded in 1999, Conexant is a privately-held fabless semiconductor and audio technology engineering company headquartered in Irvine, California with offices and design centers worldwide.