Supports single or multi-microphone processing for improved robustness and a superior user experience.
Uses a unique set of field-proven algorithms, with complete documentation and tooling, and supports VDA and ITU qualification standards for hands-free systems.
Supports configuration to nearly any microphone geometry and eliminates tuning efforts.
VoCon SSE is available for fixed-point and floating-point processors and can be used on nearly every 32bit general purpose processor or DSP.
VoCon SSE has been commercially used in the automotive domain for more than 15 years. It delivers optimal hands-free communication and speech recognition results when used with VoCon Hybrid or Dragon Drive.
Empowers far talk operation of home entertainment and appliances.
Supports robust voice recognition and hands-free communication in noisy environments like offices and public places.
Wind noise suppression
Built-in single- and multi-channel wind-noise suppression algorithm eliminates the effect of noise caused by climate control fans, open windows or convertible tops.
Echo and noise suppression
Improves the microphone signal resulting in more audible telephone conversations and better speech recognition performance.
Non-stationary noise suppression
Effectively removes noise caused by road-bumps with minimal speech distortion.
High-quality noise reduction
Delivers 10-12 dB noise reduction with frequency dependent noise attenuation to increase perception of sound quality.
Talk over barge-in with VoCon SSE allows the user to speak over spoken dialog prompts and be recognized.
Adaptive microphone self-calibration
Improves robustness of adaptive beamformer against microphone mismatch.
Beamforming and post-filtering
Separates unwanted signals such as interfering speech and background noises from the desired speech signal to achieve a high degree of directionality with a low number of microphones.
Robust full duplex echo-canceller (Type 1)
Mono / stereo echo-canceller eliminates trade-off between echo suppression and double-talk performance.
Text-to-speech solution that enriches the user experience with enhanced expressivity by generating high quality and natural sounding speech.
A feature-rich, high-performance development suite for embedded and connected speech recognition applications.