What is good, better, and the best audio? For WinHEC Cortana Workshop, Shenzhen, 11 August 2015
2.0 Laptop as a Speakerphone Enterprise Class Full Duplex Speakerphone Experience Optimized for MS Lync/Skype CONEXANT AudioSmart TM Software Flawless Cortana Accuracy SSP Input Noise Reduction Audio Output >2X Louder mHD-Audio Output Enhancement or I 2 S / I 2 C No Risk to Speakers SoftAware Speaker Control CONEXANT CODEC Better Media Consumption with Integrated AudioSmart Amp experience Sound Pressure Level at 1m Original System AudioSmart System USB Speakerphone (benchmark) 65dB 81dB 76dB No other solution can deliver full duplex conference speakerphone experience while concurrently delivering this level of loudness from laptop or tablet form factor Company Confidential and Proprietary 2
A UDIO S MART TM INPUT TECHNOLOGY Conexant Confidential and Proprietary 3
Conexant Smart Source Pickup (SSP) SSP: Conexant proprietary noise suppression algorithm. The one easy solution. • Based on a Blind Source Separation technique, modified for real-world robustness. • NOT Beamforming ; SSP uses spatial representation of target speech and noise sources to reduce stationary and semi non-stationary interference (i.e., babble noise). • Speech can be at any angle relative to the microphones. • Noise can be at any angle relative to the microphones, even in the same direction as the speech. Full-Sphere “User” “Noise” Conexant Confidential and Proprietary 4
SSP Voice + Speech Algorithm Value Proposition Conexant’s Smart Source Pickup Input Pre-Processing Solution with 5M Technology Enables: • High resolution VoIP + class-leading Automatic Speech Recognition from up to 5 meters (16 feet) away! Intelligible • Clear voice quality calls and videoconferencing in real-world Voice Calls conditions (i.e., across a large, noisy room). Increased Conexant VoIP Voice/Speech Input Clarity Pre-Processing Decreased Speech Word Recognition Error Rate Engine Speech + Interference Clear Speech Conexant Confidential and Proprietary 5
SSP Versatility Supports all device orientations and use-cases with only 2 MICs, NO holes drilled in glass, and ZERO user input! Clamshell Stand Tent Tablet Lay-Flat Company Confidential and Proprietary 6
A UDIO S MART TM OUTPUT TECHNOLOGY Conexant Confidential and Proprietary 7
Class-D Power Optimization Constantly delivers DSP-optimized signal to speakers at maximum safe power level, independent of software Actual output power of H-bridge is monitored at chip pins (closed loop!) and intelligently averaged 100% in hardware Closed-loop system actively monitors speaker power consumption Output RMS is compared to a programmable threshold matching exact speaker capabilities RMS measurements drive intelligent gain control Adjustments are time-windowed to avoid false triggers by spikes in audio content PGA DAC Class-D Speaker Amplifier decrement gain during excess RMS output RMS Conexant Confidential and Proprietary 8
A UDIO S MART TM IOT EXAMPLE Conexant Confidential and Proprietary 9
2.0 Speaker Performance Comparison Amazon Echo Conexant Smart Speaker Seven Microphones • • Two Microphones • Amazon Voice Processing Conexant Far-Field Voice Processing • Amazon voice trigger engine • • Sensory voice trigger engine (embedded in Conexant SOC) Company Confidential and Proprietary 10
Conexant Noise Suppression Performance vs Amazon ~ 40% Hit Rate improvement in noisy conditions (Noise 5dB lower than speech) No Hit Rate degradation in “clean” conditions (Noise 10dB lower than speech) 30% Hit Rate improvement in extremely noise conditions (Noise same level as speech) With Conexant processing, user will be understood one in three attempts With Amazon processing, user will almost never be understood Company Confidential and Proprietary 11
A UDIO S MART TM ABOUT CONEXANT Conexant Confidential and Proprietary 12
History of Conexant Audio 20+ years of Audio Signal Processing Expertise 20+ years of Audio Hardware Expertise <2000 2006 2010 2012 2014 Windows APO USB codec in Low-power PC audio Library complements production headsets, codec in production HW portfolio speakers and computers Acoustic Echo speakerphones DSP codec with Cancellation enables AudioSmart TM Class-D DSP Codec for high integrated Class D in speakerphone in Integrated with Codec quality Voice Input production systems production and Communication Expanded PC audio Fax/Modems in Tier 1 TVs portfolio (ADI acquisition) Company Confidential and Proprietary 13
Summary • Single supplier providing Silicon & Software optimized to work “better together” – Silicon – High Performance ADC, DAC, CODEC’s, DSP & Smart AMP – Software – Input Processing, Playback Processing & Awareness – Ecosystems – Driving end user use cases with Industry leaders – Partnerships – partners telling OEM’s – “Conexant’s solutions work better” – Applications – support Audio for PC/Tablets/Headset/Docks/Smart Home/IoT Company Confidential and Proprietary 14
Worldwide, World-Class Support • Highest concentration of France computer audio systems knowledge in the industry • Expert Support AND Korea Engineering staff in every major Japan China time zone • Proven track record enabling Taiwan India on-time shipment of Tier-1 OEM products Singapore Headquarters Waltham Design Centers Sales Offices Design & Sales Headquarters Irvine Austin * Supported through a network of 20 Distributors and 13 Rep Firms Company Confidential and Proprietary 15
Recommend
More recommend
