July 5, 2017 -
Conexant, a leading provider of audio and voice technology solutions that enable a more natural user experience, will work with Baidu to release development kits and reference designs for device makers to develop voice-enabled artificial intelligent (AI) devices running on Baidu’s DuerOS platform.
DuerOS is a conversation-based AI system that supports access to a voice-activated digital assistant for mobile phones, TVs, speakers, and other devices.
“The voice revolution is a global phenomenon. By working with Baidu, we help more third-party manufacturers bring to market innovative voice-enabled AI devices with an exceptional conversational AI experience,” said Saleel Awsare, President of Conexant. “The launch of DuerOS development kits and reference designs will drastically reduce development time and cost, allowing manufacturers to quickly bring their innovative ideas to market.”
Enabling speech recognition and voice control from a distance requires overcoming substantial acoustic challenges related to echo cancellation, background noise, position of microphones, speaker placement and more. Conexant’s 2-mic and 4-mic development kits for DuerOS will help shorten time-to-market of conversation-based AI devices with high-performance noise cancellation and far-field voice capability.
The development kits and reference designs will be powered by Conexant’s CX20924 4-microphone and CX20921 2-microphone voice input processing solutions. The collaboration is aimed at helping developers and device-makers integrate DuerOS into their own products.
The main component in the new development kits is Conexant’s AudioSmart voice input processor running its industry-leading far-field voice pre-processing software technology.
Key benefits of the Conexant AudioSmart voice input processors include: (i) robust far-field voice interaction with two or four microphones; (ii) proprietary Smart Source Locator technology which identifies the direction from which the user’s voice is coming (4-mic only); (iii) enhanced Smart Source Pickup noise suppression, which improves speech recognition performance by filtering non-stationary TV noise and voices coming from sources other than the user out of the audio signal; and (iv) voice barge-in enabled by full duplex acoustic echo cancellation (AEC), which detects an active voice even when the device is playing music.
Conexant’s far-field voice input processors also focus on the user’s voice and remove echoes and noise from the audio signal to provide the DuerOS cloud AI platform with clear voice requests for speech recognition processing.
“Conexant brings a valuable asset to Baidu and third-party product developers looking to create innovative applications for the DuerOS AI platform,” said Kun Jing, General Manager of Baidu Duer Business Unit. “Voice interface is a critical part of DuerOS and we are committed to working closely with Conexant to quickly grow the DuerOS ecosystem by offering product developers a solution to help them quickly fulfill consumer demand for top-performing AI-infused devices. We’re working closely with Conexant to ensure their voice solutions provide optimal speech recognition performance with our AI system and are excited to provide device makers tools to jump start the creation of new hardware applications.”