Qualcomm Incorporated

Tusimple, Inc.

Createai, Inc.

Song Wang

Eddie L T Choy

Dinesh Ramakrishnan

Samir Kumar Gupta

Soumya Das

Arungundram C Mahendran

Prajakt Kulkarni

Sanghyun Chi

Lindong Sun

Yidi Zhang

Chang Joon Rhee

Rajat Prakash

Arnaud Meylan

Jay Kumar Sundararajan

Karthika Paladugu

Pei Xiang

Hyun Jin Park

Soham Sheth

Aris Balatsos

Manu Sharma

David William Craig

Deepak Kumar Challa

Homayoun Shahri

Niranjan Ramesh Pendharkar

Ravi Satyanarayanan

Prajakt V Kulkarni

Eddie LT Choy

A workflow management system is described to manage tasks to be performed with vehicles. The workflow management system includes a workflow management server and a computer located in a vehicle. The workflow management server generates and sends to the computer a record that describes a task to be performed with a vehicle. The task may include collecting sensor data from one or more sensors on the vehicle, or performing a vehicle driving test using an updated operating system to be used by the vehicle. The record can include a starting location and a destination of a route on which the vehicle is to perform the task. The computer receives the record, executes an operating system of the vehicle to perform the task, determines that the task is completed, and sends to a database a record status information that indicates that the task is completed.

Workflow management system

Methods, systems, and devices are described for assessing the quality of end-to-end connectivity for a wireless communication device. Data generated from at least one of existing traffic and networking operations caused by existing traffic of the wireless communication device may be monitored to obtain information related to connectivity quality. One or more values of one or more metrics may be determined using the obtained information. The quality of end-to-end connectivity for the wireless communication device may be assessed using the value(s) of the metric(s). Based at least in part on a result of the assessment, an action may be performed to improve connectivity quality for the wireless communication.

Determination of end-to-end transport quality

Systems and methods are described herein for providing a virtual conference using a master device implemented with a personal communication device (PCD), including determining, by the master device, a latency for each of a plurality of satellite devices connected to the master device. The master device then determines an uplink buffer duration based on a difference between a highest latency and a lowest latency among the plurality of satellite devices. The master device determines a processing time for an uplink data packet, the processing time being determined based, at least in part, on the uplink buffer duration. The master device then performs signal processing at the processing time for the received uplink data packets.

Methods and systems for virtual conference system using personal communication devices

Systems and methods are described herein for providing a virtual conference with a master device connected to a plurality of satellite devices, including: receiving, by the master device, uplink data packets from a plurality of channels, each of the plurality of channels is associated with one of the plurality of satellite devices, and dividing, by the master device, the plurality of channels into two or more groups based on a conversation captured in the uplink data packets of each of the plurality of channels. The master device selects one group from the two or more groups for output. The master device also transmits downlink data packets corresponding to the selected group for the plurality of satellite devices.

In general, techniques are described for limiting active noise cancellation output. As one example, an apparatus comprising one or more processors may perform the techniques. The one or more processors may be configured to, when an estimated noise level increases, dynamically lowering application of active noise cancellation to at least a portion of an audio signal to obtain at least a portion of an active noise cancelled version of the audio signal.

Limiting active noise cancellation output

Signal processing solutions take advantage of microphones located on different devices and improve the quality of transmitted voice signals in a communication system. With usage of various devices such as Bluetooth headsets, wired headsets and the like in conjunction with mobile handsets, multiple microphones located on different devices are exploited for improving performance and/or voice quality in a communication system. Audio signals are recorded by microphones on different devices and processed to produce various benefits, such as improved voice quality, background noise reduction, voice activity detection and the like.

Speech enhancement using multiple microphones on multiple devices

Voice activity detection using multiple microphones can be based on a relationship between an energy at each of a speech reference microphone and a noise reference microphone. The energy output from each of the speech reference microphone and the noise reference microphone can be determined. A speech to noise energy ratio can be determined and compared to a predetermined voice activity threshold. In another embodiment, the absolute value of the autocorrelation of the speech and noise reference signals are determined and a ratio based on autocorrelation values is determined. Ratios that exceed the predetermined threshold can indicate the presence of a voice signal. The speech and noise energies or autocorrelations can be determined using a weighted average or over a discrete frame size.

Multiple microphone voice activity detector

A method for suppressing ambient noise using multiple audio signals may include providing at least two audio signals captured by at least two electro-acoustic transducers. The at least two audio signals may include desired audio and ambient noise. The method may also include performing beamforming on the at least two audio signals in order to obtain a desired audio reference signal that is separate from a noise reference signal.

Methods and apparatus for suppressing ambient noise using multiple audio signals

In a digital system with more than one clock source, lack of synchronization between the clock sources may cause overflow or underflow in sample buffers, also called sample slipping. Sample slipping may lead to undesirable artifacts in the processed signal due to discontinuities introduced by the addition or removal of extra samples. To smooth out discontinuities caused by sample slipping, samples are filtered to when a buffer overflow condition occurs, and the samples are interpolated to produce additional samples when a buffer underflow condition occurs. The interpolated samples may also be filtered. The filtering and interpolation operations can be readily implemented without adding significant burden to the computational complexity of a real-time digital system.

Resolving buffer underflow/overflow in a digital system

An electronic device for suppressing noise in an audio signal is described. The electronic device includes a processor and instructions stored in memory. The electronic device receives an input audio signal and computes an overall noise estimate based on a stationary noise estimate, a non-stationary noise estimate and an excess noise estimate. The electronic device also computes an adaptive factor based on an input Signal-to-Noise Ratio (SNR) and one or more SNR limits. A set of gains is also computed using a spectral expansion gain function. The spectral expansion gain function is based on the overall noise estimate and the adaptive factor. The electronic device also applies the set of gains to the input audio signal to produce a noise-suppressed audio signal and provides the noise-suppressed audio signal.

Suppressing noise in an audio signal

Sound signal reception is improved by utilizing a plurality of microphones to capture sound signals which are then weighed to dynamically adjust signal quality. A first sound signal and a second sound signal are obtained from first and second microphones, respectively, where the first and second sound signals originate from one or more sound sources. A first signal characteristic (e.g., signal power, signal signal-to-noise ratio, etc.) is obtained for the first sound signal and a second signal characteristic is obtained for the second sound signal. The first and second sound signals are weighed or scaled based on their respective first and second signal characteristics. The weighed first and second sound signals are then combined to obtain an output sound signal.

Sound quality by intelligently selecting between signals from a plurality of microphones

A mechanism is provided that monitors secondary microphone signals, in a multi-microphone mobile device, to warn the user if one or more secondary microphones are covered while the mobile device is in use. In one example, smoothly averaged power estimates of the secondary microphones may be computed and compared against the noise floor estimate of a primary microphone. Microphone covering detection may be made by comparing the secondary microphone smooth power estimates to the noise floor estimate for the primary microphone. In another example, the noise floor estimates for the primary and secondary microphone signals may be compared to the difference in the sensitivity of the first and second microphones to determine if the secondary microphone is covered. Once detection is made, a warning signal may be generated and issued to the user.

Signaling microphone covering to the user

An enhanced blind source separation technique is provided to improve separation of highly correlated signal mixtures. A beamforming algorithm is used to precondition correlated first and second input signals in order to avoid indeterminacy problems typically associated with blind source separation. The beamforming algorithm may apply spatial filters to the first signal and second signal in order to amplify signals from a first direction while attenuating signals from other directions. Such directionality may serve to amplify a desired speech signal in the first signal and attenuate the desired speech signal from the second signal. Blind source separation is then performed on the beamformer output signals to separate the desired speech signal and the ambient noise and reconstruct an estimate of the desired speech signal. To enhance the operation of the beamformer and/or blind source separation, calibration may be performed at one or more stages.

Enhanced blind source separation algorithm for highly correlated mixtures

Techniques of this disclosure provide for adjustment of a conversion rate of a sampling rate converter (SRC) in real-time. The SRC determines relative timing of generated output samples based on non-approximated integer components that are recursively updated. The SRC may further base relative timing of output samples on a value of one or more step size components associated with the integer components. Also according to techniques of this disclosure, a conversion rate of an SRC may be adjusted in real-time based on a detected mismatch between a source clock of a digital input signal and a local clock.

Growing community of inventors

San Diego, CA, United States of America

Song Wang