Baidu is the leading Chinese language Internet search provider and, as any technology-based media company, it intends to lead the way in the adoption of voice assistants, especially for Chinese language markets. Baidu recognizes that 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. That was the main motivation to reach out to Conexant, an already established supplier of audio and voice solutions for such applications.
The collaboration is aimed at helping developers and device-makers integrate DuerOS into their own products, and leveraging all the power of Conexant’s far-field solution for voice-enabled products. The 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. Through this partnership, Baidu and Conexant are establishing a high-performance standard for AI devices to come.
“Conexant brings a valuable asset to Baidu and third-party product developers looking to create innovative applications for the DuerOS AI platform,” says 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 jumpstart the creation of new hardware applications.”
The core component in the announced development kits is Conexant’s AudioSmart voice input processor (CX20924 for 4-mic applications, and CX20921 for 2-mic applications) running its industry-leading far-field voice pre-processing software technology. Conexant’s far-field voice input processors focus on the user’s voice and remove echoes and noise from the audio signal to provide the DuerOS cloud AI platform clear voice requests for speech recognition processing.
“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,” says Saleel Awsare, Conexant’s President. “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.”
In November 2016, Baidu released as open source the first Chinese language APIs for its four key speech technologies: Long Utterance Speech Recognition, Far-Field Speech Recognition, Expressive Speech Synthesis and Wake Word. These speech technologies have since been used in the development of a range of products and services from Baidu and partners. Baidu launched its first speech recognition in 2013 and has since seen rapid growth in speech use. In just three years, the daily requests for speech recognition grew from 5 million in 2013 to 140 million in 2016, and the number of daily requests for speech synthesis surpasses 200 million. In the meantime, the number of developers using Baidu’s speech system has also grown to more than 140,000!
Introduced at Baidu Create 2017, the development kits and reference designs for DuerOS are now available.
www.conexant.com | www.baidu.com