Qualcomm Incorporated

Prajakt Kulkarni

Suresh Devalapalli

Samir Kumar Gupta

Nidish Ramachandra Kamath

Eddie L T Choy

Erik Visser

Pei Xiang

Lae-Hoon Kim

Stephen A Molloy

Sunkuk Moon

Yinyi Guo

Song Wang

Haoping Xu

Bohuslav Rychlik

Matthew Levi Severson

Seyfollah Seyfollahi Bazarjani

Jeffrey Mark Hinrichs

Ren Li

George Patsilaras

Guoqing Miao

Jeffrey Gemar

Joseph Robert Fitzgerald

Aaron Douglass Lamb

Allister Alemania

Kuntal Dilipsinh Sampat

Justin Joseph Rosen Gagne

Gene Hyde McAllister

Robert J Vachon

Suren Mohan

Alex Jong

Satish Goverdhan

Jan Paul Van Der Wagt

Engin Ipek

Lakshmi Narayana Macha

Hiren Bhagatwala

Andrew Kostic

Fahad Ali

Can Hankendi

Shiqi Sun

Suze Balatsos

Xiaoxuan Yu

Sheng Zhan

Zhaohui Du

Nanda Kumar Aswatha Kumar

Srivatsan Srinivasan

A device to perform target sound detection includes a memory including a buffer configured to store audio data. The device includes one or more processors coupled to the memory. The one or more processors are configured to receive the audio data from the buffer. The one or more processors are configured to detect the presence or absence of one or more target non-speech sounds in the audio data. The one or more processors are further configured to generate a user interface signal, to indicate one of the one or more target non-speech sounds has been detected, and provide the user interface signal to an output device. The device further comprises the output device that is configured to output a visual representation associated with the one of the one or more target non-speech sounds has been detected.

Method and apparatus for target sound detection

A device to process speech includes a speech processing network that includes an input configured to receive audio data. The speech processing network also includes one or more network layers configured to process the audio data to generate a network output. The speech processing network includes an output configured to be coupled to multiple speech application modules to enable the network output to be provided as a common input to each of the multiple speech application modules.

Shared speech processing network for multiple speech applications

Systems and techniques are provided for compressing data. A process can include generating a compressed sub-packet by removing one or more sparsity bytes from a sequence of values corresponding to a sub-packet, the sequence of values including one or more sparsity bytes each equal to a configured sparsity value and one or more non-sparsity bytes each corresponding to a respective data value different from the configured sparsity value. A sub-packet header can be generated for the compressed sub-packet, and indicative of a respective location within the sequence of values of each non-sparsity byte. A packet header can be generated for a plurality of compressed sub-packets, and indicative of the configured sparsity value and respective coding information for each compressed sub-packet. A compressed data packet can be generated to include at least the packet header, the sub-packet header, and the one or more non-sparsity bytes included in the sequence of values.

Packet-based universal bit-field masking coding using configurable sparsity information

A device to perform target sound detection includes one or more processors. The one or more processors include a buffer configured to store audio data and a target sound detector. The target sound detector includes a first stage and a second stage. The first stage includes a binary target sound classifier configured to process the audio data. The first stage is configured to activate the second stage in response to detection of a target sound. The second stage is configured to receive the audio data from the buffer in response to the detection of the target sound.

Various embodiments include methods and devices for compression and decompression of weight data sets. Some embodiments may include compressing weight data by receiving a weight data set of binary numbers representing weight values, generating a frame payload including a compressed first frame of a first subset of the weight values in the weight data set, and generating a block of compressed weight data having the frame payload. Some embodiments may include decompressing weight data by retrieving a block of compressed weight data, in which the block of compressed weight data includes a frame header associated with a frame payload, in which the frame header includes a normalization factor indicator, and in which the frame payload includes compressed weight values, and generating a first decompressed frame comprising decompressed weight values of the compressed weight values of the frame payload.

Compression technique for deep neural network weights

A device to process speech includes a speech processing network that includes an input configured to receive audio data corresponding to audio captured by one or more microphones. The speech processing network also includes one or more network layers configured to process the audio data to generate a network output. The speech processing network includes an output configured to be coupled to multiple speech application modules to enable the network output to be provided as a common input to each of the multiple speech application modules. A first speech application module corresponds to a speaker verifier, and a second speech application module corresponds to a speech recognition network.

The energy consumed by data transfer in a computing device may be reduced by transferring data that has been encoded in a manner that reduces the number of one '1' data values, the number of signal level transitions, or both. A data destination component of the computing device may receive data encoded in such a manner from a data source component of the computing device over a data communication interconnect, such as an off-chip interconnect. The data may be encoded using minimum Hamming weight encoding, which reduces the number of one '1' data values. The received data may be decoded using minimum Hamming weight decoding. For other computing devices, the data may be encoded using maximum Hamming weight encoding, which increases the number of one &#x201c;1&#x201d; data values while reducing the number of zero &#x201c;0&#x201d; values, if reducing the number of zero values reduces energy consumption.

Data re-encoding for energy-efficient data transfer in a computing device

A device to process speech includes a speech processing network that includes an input configured to receive audio data corresponding to audio captured by one or more microphones. The speech processing network also includes one or more network layers configured to process the audio data to generate an output representation of the audio data. The speech processing network includes an output configured to be coupled to multiple speech application modules to enable the output representation to be provided as a common input to each of the multiple speech application modules.

Methods, systems, and devices for systems and techniques for processing keywords in audio data are described. In some devices configured with a virtual assistant, an audio processing component may support a command-first, keyword-second voice activation procedure. The audio processing component may receive audio data from a microphone and may compress a portion of the audio data and store the compressed audio data in a first buffer and may store a portion of the audio data that is uncompressed in a second buffer. The audio processing component may use the uncompressed audio data to detect the presence of a keyword and use the compressed audio data to identify a command associated with the keyword. Upon detection of the keyword, the audio processing component may decompress the compressed audio data and transmit the decompressed audio data and the uncompressed audio data to a main processor of the device.

Systems and techniques for processing keywords in audio data

A mobile device may include at least one processor configured to generate a first set and second set of processed audio signals for use in a surround sound system. The mobile device may also include at least one output port adapted to provide the first set of processed audio signals for use in the surround sound system to at least two speakers. The mobile device may also include an output port adapted to provide the second set of processed audio signals for use in the surround sound system to headphone speakers.

Systems and methods for providing surround sound using speakers and headphones

A system and method of improving the efficiency in the power consumption of an audio system. In essence, the technique is to adjust the power delivered from the power supply to the analog section, such as the power amplifier, in response to the volume level indicated by the volume control module and/or in response to the detected characteristic of the input audio signal. Thus, in this manner, the analog section is operated in a manner that is related to the level of the signal it is processing. Additionally, the system and method also relate to a technique of adjusting the dynamic ranges of the digital signal and the analog signal to improve the overall dynamic range of the system without needing to consume additional power.

System and method of reducing power consumption for audio playback

Embodiments of methods, apparatuses, devices and systems associated with combining or mixing digital media streams are disclosed.

System, method or apparatus for combining multiple streams of media data

A method for providing variable root note support in an audio player is described. A file with Musical Instrument Digital Interface (MIDI) data and a set of user defined instruments is received. A metric is determined using a user defined root note in the user defined instruments, a key number for a MIDI note in the MIDI data, and a player specific root note. The key number is adjusted based on the metric.

Systems and methods for providing variable root note support in an audio player

A method for providing multi-region instrument support in an audio player is described. A set of user defined instruments and a set of MIDI data is received. At least one multi-region instrument in the set of user defined instruments is identified. Each region in the multi-region instruments is mapped to a single region instrument with the same parameters as the region. A new instrument number is assigned to each single region instrument. The MIDI data is modified based on the mapping and assigning.

Systems and methods for providing multi-region instrument support in an audio player

In accordance with a method for providing a distinct perceptual location for an audio source within an audio mixture, a foreground signal may be processed to provide a foreground perceptual angle for the foreground signal. The foreground signal may also be processed to provide a desired attenuation level for the foreground signal. A background signal may be processed to provide a background perceptual angle for the background signal. The background signal may also be processed to provide a desired attenuation level for the background signal. The foreground signal and the background signal may be combined into an output audio source.

Growing community of inventors

San Diego, CA, United States of America

Prajakt Kulkarni