Possess microphone array, signal processing, AI engine, services platform, system integration and other complete core technologies
Support wake-up interruption, speech recognition of far and near field, image recognition, semantics understanding, multi-tone speech synthesis and relevant offline engine solution
Adapt to different chip platform and operating system, provide various solutions from software SDK to overall design
Cooperate with ability and content provider, support secondary development, free custom and multi-dimensional operation
Provide complete turnkey solution with integration of hardware and software
Provide capabilities of autonomous positioning navigation, intelligent voice dialogue, accurate face recognition, commodity knowledge graph, customized enterprise knowledge data, and let robot provide consultation and introduction, propaganda and presentation, direction and other services
Support online and offline voice control of all kinds of household appliances, possess accurate cold wake-up, rich colloquial instruction, recognition of mandarin and dialect, ambient noise rejection and other capacities
Provide hot and cold wake-up, far field recognition, various audial-on-demand dimensions and control instructions, to easily get audio content and better control equipment at home
Provide human-computer interaction solution under on-board environment, support owner's business and information acquisition under in-car scenes, services near around geographic position to realize safer and more efficient operation
Provide customized and optimized voice-recognition service, pure dialogue engine and rich early education resources based on children ' s features of all ages
Linear Annular Annular+ Center Array
2-8mic
Voice Enhancement Sound Localization
Reverberation Elimination
Noise Abatement Echo Cancellation
Distant accurate wake-up under the environment of household and equipment Noise
Optimized identification engine for specific field
Authentication mode best for speech interaction
Multi-angle face detection and recognition under household lighting conditions
High recognition rate for dynamic and static gestures, just lift a finger
With friendly children's sound, make expression of equipment more fluent
Support Qualcomm, MTK, Allwinner, ACTS-US, Rockchips
Support Android/Linux/RTOS
CI1006 intelligent speech neural network processing chip
Support SDK, PCBA
Refer to the design for output in different ways
Artificial intelligence interactive engine, receive and understand images, sound and various sensor information
Enable to provide cross-scene and cross-device dialogue, and support IoT operation
Based on front-end signal equipment, VUI can realize gentle wake-up and interruption of far field
Constant dialogue without wake-up in special application, to provide user with more convenient experience
Forgetting strategies for long and short periods combined with context
Recommended active dialogue based on triggering condition, user portrait and scene
Support different user portraits
Multi-lingual interaction interface of Chinese, English and Russian
Integrate multiple platforms, a real SaaS overall solution, think what the customer wants, provide rapid configuration and production; Adopt to specific needs, docking ability and content servicer to realize tripartite wins.
Provide developer with the ability of self-built contents and services, meet self-use and output of personalized contents and services
Deliver the full process operation to client to make product have the vitality; provide visualization of product operation index, so as to ensure that user experience is effectively guaranteed
Business Cooperation
liushulan@roobo.comTechnical Support
yangkun@roobo.com