Diotek's speech recognition engine complements Conexant’s digital audio processor, which features a comprehensive collection of pre- and post-processing algorithms and far-field voice input technology. The joint solution is targeted for smart home appliances, consumer electronics and educational toys, and brings to market a high-performance, cost-optimized platform.
Target areas of automatic speech recognition (ASR) segmentation include voice wake speech recognition – power-on scenario with no audio playback and magic word scenario with audio playback. The engine enables keyword recognition with full ASR on-chip parameter feature extraction, lookup, recognition, and fixed words library. It also supports natural language thanks to cloud-based recognition and response.
The CX20805 from Conexant is a dual-core 32-bit, high-performance, low-power digital audio processor targeted to applications with the most demanding audio requirements. Based on the Conexant Audio Processing Engine (CAPE) architecture with scalable performance of up to 800 MIPS, the CX20805 integrates high-speed USB 2.0 and other key audio interfaces with advanced power management functionality.
Visit Conexant Systems at www.conexant.com