Cisco Technology, Inc.

Future Wei Technologies, Inc.

Cisco Systems Inc.

Fuling Liu

Wei Li

Wei-Lien Hsu

Eric Chen

Herbert M K Chen

Xinmin Yan

Xilin Li

Systems, methods, and devices are disclosed for detecting an active speaker in a two-way conference. Real time audio in one or more sub band domains are analyzed according to an echo canceller model. Based on the analyzed real time audio, one or more audio metrics are determined from output from an acoustic echo cancellation linear filter. The one or more audio metrics are weighted based on a priority, and a speaker status is determined based on the weighted one or more audio metrics being analyzed according to an active speaker detection model. For an active speaker status, one or more residual echo or noise is removed from the real time audio based on the one or more audio metrics.

Acoustic echo cancellation based sub band domain active speaker detection for audio and video conferencing applications

Systems, methods, and devices are disclosed for detecting an active speaker in a two-way conference. Real time audio in one or more sub band domains are analyzed according to an echo cancellor model. Based on the analyzed real time audio, one or more audio metrics are determined from output from an acoustic echo cancellation linear filter. The one or more audio metrics are weighted based on a priority, and a speaker status is determined based on the weighted one or more audio metrics being analyzed according to an active speaker detection model. For an active speaker status, one or more residual echo or noise is removed from the real time audio based on the one or more audio metrics.

An echo cancellation method includes receiving an echo reference signal, receiving a microphone signal, decomposing, with a first filter bank, the echo reference signal into a series of subband echo reference signals, decomposing, with a second filter bank, the microphone signal into a series of subband microphone signals, estimating a group delay between the echo reference signal and the microphone signal using the series of subband echo reference signals and the series of subband microphone signals, estimating, using adaptive filters, acoustic echoes in the echo reference signal based at least in part on the group delay, subtracting the acoustic echoes from the series of subband microphone signals to obtain a series of acoustic echo removed subband signals, combining the series of acoustic echo removed subband signals into a single time domain echo removed signal, and sending the single time domain echo removed signal to a host operating system.

Acoustic echo cancellation with delay uncertainty and delay change

System and method embodiments are provided for coordinated hardware and software performance monitoring to determine a suitable polling time for memory cache during run time. The system and method adapt to the time-varying software workload by determining a next polling time based on captured local characteristics of memory access pattern over time. The adaptive adjustment of polling time according to system performance and dynamic software workload allows capturing more accurately the local characteristics of memory access pattern. An embodiment method includes capturing, at a current polling instance, hardware performance parameters to manage the memory cache, and adjusting a time interval for a next polling instance according to the hardware performance parameters. The captured hardware performance parameters are used to compute performance metrics, which are then used to determine the time interval for the next polling instance.

System and method for software/hardware coordinated adaptive performance monitoring

The present invention relates to a system and method for canceling echoes from telecommunications networks by providing a multi-adaptation echo canceller. Unlike conventional TDM echo cancellers, the present invention uses at least two echo cancellers arranged in a novel manner to cancel echoes generated by a voice packet associated with an IP network or the like. The present invention further provides a double adaptation echo canceller that transfers coefficients from a first echo canceller to a second echo canceller. The present system compares the single and double adaptation echo error signals and selects the echo canceller with the smaller error signal. This process is continuously repeated so that the system can select the optimal echo canceller for canceling echoes for each voice block/packet. The present invention can be implemented with any number of echo cancellers so long as the each block or packet can be processed within a specified time frame.

Growing community of inventors

San Jose, CA, United States of America

Fuling Liu