Qualcomm Incorporated

Stephane Pierre Villette

Daniel Jared Sinder

Vivek Rajendran

Venkatesh Krishnan

Pravin Kumar Ramadas

Venkatraman Atti

Subasingha Shaminda Subasingha

Sen Li

Venkata Subrahmanyam Chandra Sekhar Chebiyyam

Michel Adib Sarkis

Scott David Beith

Suzana Arellano

Ke-Li Cheng

Matthew Fischler

Venkatraman Srinivasa Atti

Venkatraman S Atti

A device includes a memory and one or more processors configured to process sensor data to determine a semantical context associated with the sensor data. The one or more processors are also configured to generate adjusted face data based on the determined semantical context and face data. The adjusted face data includes an avatar facial expression that corresponds to the semantical context.

Avatar facial expressions based on semantical context

A device includes a memory configured to store a collection of sets of weights, each of the sets of weights representing a respective media segment. The device also includes one or more processors configured to generate data representing the detected first input speech segment and to pass the data representing the detected first input speech segment into a collection of memory units. Each memory unit of the collection of memory units includes a set of weights from the collection of sets of weights. The one or more processors are also configured to generate a first estimate of an associated media segment that represents the detected first input speech segment. The associated media segment corresponds to a first memory unit in the collection of memory units.

Media segment representation using fixed weights

A device includes one or more processors configured to input one or more segments of an input media stream into a feature extractor. The one or more processors are further configured to pass an output of the feature extractor into an utterance classifier to produce at least one representation of at least one utterance class of a plurality of utterance classes. The one or more processors are further configured to pass the output of the feature extractor and the at least one representation into a segment matcher to produce a media output segment identifier.

Media segment prediction for media generation

Methods, systems, and devices for encoding are described. A device, which may be otherwise known as user equipment (UE), may support standards-compatible audio encoding (e.g., speech encoding) using a pre-encoded database. The device may receive a digital representation of an audio signal and identify, based on receiving the digital representation of the audio signal, a database that is pre-encoded according to a coding standard and that includes a quantity of digital representations of other audio signals. The device may encode the digital representation of the audio signal using a machine learning scheme and information from the database pre-encoded according to the coding standard. The device may generate a bitstream of the digital representation that is compatible with the coding standard based on encoding the digital representation of the audio signal, and output a representation of the bitstream.

Speech encoding using a pre-encoded database

A method includes extracting a voicing classification parameter of an audio signal and determining a filter coefficient of a low pass filter based on the voicing classification parameter. The method also includes filtering a low-band portion of the audio signal to generate a low-band audio signal and controlling an amplitude of a temporal envelope of the low-band audio signal based on the filter coefficient. The method also includes modulating a white noise signal based on the amplitude of the temporal envelope to generate a modulated white noise signal and scaling the modulated white noise signal based on a noise gain to generate a scaled modulated white noise signal. The method also includes mixing a scaled version of the low-band audio signal with the scaled modulated white noise signal to generate a high-band excitation signal that is used to generate a decoded version of the audio signal.

High band excitation signal generation

A device includes a decoder configured to receive an encoded audio signal at a decoder and to generate a synthesized signal based on the encoded audio signal. The device further includes a classifier configured to classify the synthesized signal based on at least one parameter determined from the encoded audio signal.

Decoder audio classification

An electronic device configured for encoding a watermarked signal is described. The electronic device includes modeler circuitry. The modeler circuitry determines parameters based on a first signal and a first-pass coded signal. The electronic device also includes coder circuitry coupled to the modeler circuitry. The coder circuitry performs a first-pass coding on a second signal to obtain the first-pass coded signal and performs a second-pass coding based on the parameters to obtain a watermarked signal.

Devices for encoding and decoding a watermarked signal

A method for decoding a signal on an electronic device is described. The method includes receiving a signal. The method also includes extracting a bitstream from the signal. The method further includes performing watermark error checking on the bitstream for multiple frames. The method additionally includes determining whether watermark data is detected based on the watermark error checking. The method also includes decoding the bitstream to obtain a decoded second signal if the watermark data is not detected.

Devices for encoding and detecting a watermarked signal

A particular method includes determining, based on spectral information corresponding to an audio signal that includes a low-band portion and a high-band portion, that the audio signal includes a component corresponding to an artifact-generating condition. The method also includes filtering the high-band portion of the audio signal and generating an encoded signal. Generating the encoded signal includes determining gain information based on a ratio of a first energy corresponding to filtered high-band output to a second energy corresponding to the low-band portion to reduce an audible effect of the artifact-generating condition.

Systems and methods of performing filtering for gain determination

A particular method includes determining, at a device, a voicing classification of an input signal. The input signal corresponds to an audio signal. The method also includes controlling an amount of an envelope of a representation of the input signal based on the voicing classification. The method further includes modulating a white noise signal based on the controlled amount of the envelope. The method also includes generating a high band excitation signal based on the modulated white noise signal.

Systems and methods of performing blind bandwidth extension are disclosed. In an embodiment, a method includes determining, based on a set of low-band parameters of an audio signal, a first set of high-band parameters and a second set of high-band parameters. The method further includes generating a predicted set of high-band parameters based on a weighted combination of the first set of high-band parameters and the second set of high-band parameters.

Systems and methods of blind bandwidth extension

A method includes determining a first modeled high-band signal based on a low-band excitation signal of an audio signal, where the audio signal includes a high-band portion and a low-band portion. The method also includes determining scaling factors based on energy of sub-frames of the first modeled high-band signal and energy of corresponding sub-frames of the high-band portion of the audio signal. The method includes applying the scaling factors to a modeled high-band excitation signal to determine a scaled high-band excitation signal and determining a second modeled high-band signal based on the scaled high-band excitation signal. The method includes determining gain parameters based on the second modeled high-band signal and the high-band portion of the audio signal.

Systems and methods of energy-scaled signal processing

A device includes a decoder that includes an extractor, a predictor, a selector, and a switch. The extractor is configured to extract a first plurality of parameters from a received input signal. The input signal corresponds to an encoded audio signal. The predictor is configured to perform blind bandwidth extension by generating a second plurality of parameters independent of high band information in the input signal. The second plurality of parameters corresponds to a high band portion of the encoded audio signal. The selector is configured to select a particular mode from multiple high band modes including a first mode using the first plurality of parameters and a second mode using the second plurality of parameters. The switch is configured to output the first plurality of parameters or the second plurality of parameters based on the selected particular mode.

Bandwidth extension mode selection

A method for quantizing phase information on an electronic device is described. The method includes obtaining a speech signal. The method also includes determining a prototype pitch period signal based on the speech signal and transforming the prototype pitch period signal into a first frequency-domain signal. The method additionally includes mapping the first frequency-domain signal into a plurality of subbands. The method also includes determining a global alignment based on the first frequency-domain signal and quantizing the global alignment utilizing scalar quantization to obtain a quantized global alignment. The method additionally includes determining a plurality of band alignments corresponding to the plurality of subbands. The method also includes quantizing the plurality of band alignments utilizing vector quantization to obtain a quantized plurality of band alignments. The method further includes transmitting the quantized global alignment and the quantized plurality of band alignments.

Systems and methods for quantizing and dequantizing phase information

A method for determining pitch pulse period signal boundaries by an electronic device is described. The method includes obtaining a signal. The method also includes determining a first averaged curve based on the signal. The method further includes determining at least one first averaged curve peak position based on the first averaged curve and a threshold. The method additionally includes determining pitch pulse period signal boundaries based on the at least one first averaged curve peak position. The method also includes synthesizing a speech signal.

Growing community of inventors

San Diego, CA, United States of America

Stephane Pierre Villette