Patents by Inventor Rogerio Guedes Alves

Rogerio Guedes Alves has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20220115007
    Abstract: A device includes a memory configured to store instructions and one or more processors configured execute the instructions. The one or more processors are configured execute the instructions to receive audio data including first audio data corresponding to a first output of a first microphone and second audio data corresponding to a second output of a second microphone. The one or more processors are also configured to execute the instructions to provide the audio data to a dynamic classifier. The dynamic classifier is configured to generate a classification output corresponding to the audio data. The one or more processors are further configured to execute the instructions to determine, at least partially based on the classification output, whether the audio data corresponds to user voice activity.
    Type: Application
    Filed: May 5, 2021
    Publication date: April 14, 2022
    Inventors: Taher SHAHBAZI MIRZAHASANLOO, Rogerio Guedes ALVES, Erik VISSER, Lae-Hoon KIM
  • Publication number: 20220109930
    Abstract: Methods, systems, and devices for signal processing are described. Generally, as provided for by the described techniques, a wearable device to receive an input audio signal from one or more outer microphones, an input audio signal from one or more inner microphones, and a bone conduction signal from a bone conduction sensor based on the input audio signals. The wearable device may filter the bone conduction signal based on a set of frequencies of the input audio signals, such as a low frequency portion of the input audio signals. For example, the wearable device may apply a filter to the bone conduction signal that accounts for an error in the input audio signals. The wearable device may add a gain to the filtered bone conduction signal and may equalize the filtered bone conduction signal based on the gain. The wearable device may output an audio signal to a speaker.
    Type: Application
    Filed: November 18, 2021
    Publication date: April 7, 2022
    Inventors: Lae-Hoon Kim, Rogerio Guedes Alves, Jacob Jon Bean, Erik Visser
  • Patent number: 11259119
    Abstract: Methods, systems, and devices for signal processing are described. Generally, as provided for by the described techniques, a wearable device to receive an input audio signal from one or more outer microphones, an input audio signal from one or more inner microphones, and a bone conduction signal from a bone conduction sensor based on the input audio signals. The wearable device may filter the bone conduction signal based on a set of frequencies of the input audio signals, such as a low frequency portion of the input audio signals. For example, the wearable device may apply a filter to the bone conduction signal that accounts for an error in the input audio signals. The wearable device may add a gain to the filtered bone conduction signal and may equalize the filtered bone conduction signal based on the gain. The wearable device may output an audio signal to a speaker.
    Type: Grant
    Filed: October 6, 2020
    Date of Patent: February 22, 2022
    Assignee: QUALCOMM Incorporated
    Inventors: Lae-Hoon Kim, Rogerio Guedes Alves, Jacob Jon Bean, Erik Visser
  • Publication number: 20210409860
    Abstract: Methods, systems, computer-readable media, and apparatuses for audio signal processing are presented. A device for audio signal processing includes a memory configured to store instructions and a processor configured to execute the instructions. When executed, the instructions cause the processor to receive an external microphone signal from a first microphone and produce a hear-through component that is based on the external microphone signal and hearing compensation data. The hearing compensation data is based on an audiogram of a particular user. The instructions, when executed, further cause the processor to cause a loudspeaker to produce an audio output signal based on the hear-through component.
    Type: Application
    Filed: June 24, 2021
    Publication date: December 30, 2021
    Inventors: Jacob Jon BEAN, Rogerio Guedes ALVES, Kamlesh LAKSHMINARAYANAN, Walter Andres ZULUAGA
  • Publication number: 20210390941
    Abstract: Methods, systems, computer-readable media, devices, and apparatuses for synchronized mode transitions are presented. A first device configured to be worn at an ear includes a processor configured to, in a first contextual mode, produce an audio signal based on audio data. The processor is also configured to, in the first contextual mode, exchange a time indication of a first time with a second device. The processor is further configured to, at the first time, transition from the first contextual mode to a second contextual mode based on the time indication.
    Type: Application
    Filed: June 15, 2021
    Publication date: December 16, 2021
    Inventors: Kamlesh LAKSHMINARAYANAN, Mark Andrew ROBERTS, Jacob Jon BEAN, Walter Andres ZULUAGA, Rogerio Guedes ALVES
  • Publication number: 20210204053
    Abstract: Methods, systems, and devices for signal processing are described. Generally, as provided for by the described techniques, a wearable device may receive an input audio signal (e.g., including both an external signal and a self-voice signal). The wearable device may detect the self-voice signal in the input audio signal based on a self-voice activity detection (SVAD) procedure, and may implement the described techniques based thereon. The wearable device may perform beamforming operations or other separation procedures to isolate the external signal and the self-voice signal from the input audio signal. The wearable device may apply a first filter to the external signal, and a second filter to the self-voice signal. The wearable device may then mix the filtered signals, and generate an output signal that sounds natural to the user.
    Type: Application
    Filed: March 15, 2021
    Publication date: July 1, 2021
    Inventors: Lae-Hoon KIM, Dongmei WANG, Fatemeh SAKI, Taher SHAHBAZI MIRZAHASANLOO, Erik VISSER, Rogerio Guedes ALVES
  • Patent number: 10951975
    Abstract: Methods, systems, and devices for signal processing are described. Generally, in one example as provided for by the described techniques, a wearable device includes a processor configured to retrieve a plurality of external microphone signals that includes audio sound from outside of the device from a memory; to separate, based on at least information from an internal microphone signal, a self-voice component from a background component; to perform a first listen-through operation on the separated self-voice component to produce a first listen-through signal; and to produce an output audio signal that is based on at least the first listen-through signal, wherein the output audio signal includes an audio zoom signal that includes audio sound of the plurality of external microphone signals.
    Type: Grant
    Filed: June 8, 2020
    Date of Patent: March 16, 2021
    Assignee: Qualcomm Incorporated
    Inventors: Lae-Hoon Kim, Dongmei Wang, Fatemeh Saki, Taher Shahbazi Mirzahasanloo, Erik Visser, Rogerio Guedes Alves
  • Patent number: 10854214
    Abstract: A device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to perform an active noise cancellation (ANC) operation on noisy input speech as captured by a first microphone, the noisy input speech as captured by a second microphone, or both, to suppress a noise level associated with the noisy input speech. The one or more processors are configured to match a second frequency spectrum of a second signal with a first frequency spectrum of a first signal. The first signal is representative of the noisy input speech as captured by the first microphone, and the second signal is representative of the noisy input speech as captured by the second microphone. The one or more processors are also configured to generate an output speech signal that is representative of input speech based on the second signal.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: December 1, 2020
    Assignee: QUALCOMM Incorporated
    Inventors: Rogerio Guedes Alves, Taher Shahbazi Mirzahasanloo, Erik Visser, Lae-Hoon Kim, Fatemeh Saki, Dongmei Wang
  • Publication number: 20200312341
    Abstract: A device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to perform an active noise cancellation (ANC) operation on noisy input speech as captured by a first microphone, the noisy input speech as captured by a second microphone, or both, to suppress a noise level associated with the noisy input speech. The one or more processors are configured to match a second frequency spectrum of a second signal with a first frequency spectrum of a first signal. The first signal is representative of the noisy input speech as captured by the first microphone, and the second signal is representative of the noisy input speech as captured by the second microphone. The one or more processors are also configured to generate an output speech signal that is representative of input speech based on the second signal.
    Type: Application
    Filed: March 29, 2019
    Publication date: October 1, 2020
    Inventors: Rogerio Guedes ALVES, Taher SHAHBAZI MIRZAHASANLOO, Erik VISSER, Lae-Hoon KIM, Fatemeh SAKI, Dongmei WANG
  • Publication number: 20200304903
    Abstract: Methods, systems, and devices for signal processing are described. Generally, in one example as provided for by the described techniques, a wearable device includes a processor configured to retrieve a plurality of external microphone signals that includes audio sound from outside of the device from a memory; to separate, based on at least information from an internal microphone signal, a self-voice component from a background component; to perform a first listen-through operation on the separated self-voice component to produce a first listen-through signal; and to produce an output audio signal that is based on at least the first listen-through signal, wherein the output audio signal includes an audio zoom signal that includes audio sound of the plurality of external microphone signals.
    Type: Application
    Filed: June 8, 2020
    Publication date: September 24, 2020
    Inventors: Lae-Hoon KIM, Dongmei WANG, Fatemeh SAKI, Taher SHAHBAZI MIRZAHASANLOO, Erik VISSER, Rogerio Guedes ALVES
  • Publication number: 20200278832
    Abstract: In general, techniques are described that enable voice activation for computing devices. A computing device configured to support an audible interface that comprises a memory and one or more processors may be configured to perform the techniques. The memory may store a first audio signal representative of an environment external to a user associated with the computing device and a second audio signal sensed by a microphone coupled to a housing of the computing device. The one or more processors may verify, based on the first audio signal and the second audio signal, that the user activated the audible interface of the computing device, and obtain, based on the verification, additional audio signals representative of one or more audible commands.
    Type: Application
    Filed: February 25, 2020
    Publication date: September 3, 2020
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves, Lae-Hoon Kim, Erik Visser, Dongmei Wang, Fatemeh Saki
  • Patent number: 10762910
    Abstract: In general, this disclosure describes techniques for seamless audio data compression control system that can respond to the increasing adaptation demands for source coding characteristics to accommodate co-existence of various devices in a personal area network. In one example, a source device includes a memory and one or more processors in communication with the memory. The memory is configured to store audio data. The one or more processors are configured to select, based on a nominal compression ratio or a streaming rate, a compression level of multiple compression levels, the multiple compression levels arranged hierarchically to allow for dynamic transitioning between the compression levels. The one or more processors are further configured to encode, based on the selected compression level of the multiple compression levels, the audio data stored to the memory.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: September 1, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves
  • Patent number: 10734006
    Abstract: In general, techniques are described by which to perform audio coding based on audio pattern recognition. A source device comprising a memory and a processor may be configured to perform the techniques. The memory may store audio data. The processor may obtain, from a plurality of categories, a category to which the audio data corresponds, and obtain, based on the category, a set of pyramid vector quantization (PVQ) parameters from a plurality of sets of PVQ parameters. The processor may also perform, based on the set of PVQ parameters, PVQ with respect to the audio data to obtain a residual identifier representative of the audio data, and specify, in the bitstream, the residual identifier.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: August 4, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves
  • Patent number: 10681452
    Abstract: Methods, systems, and devices for signal processing are described. Generally, as provided for by the described techniques, a wearable device may receive an input audio signal (e.g., including both an external signal and a self-voice signal). The wearable device may detect the self-voice signal in the input audio signal based on a self-voice activity detection (SVAD) procedure, and may implement the described techniques based thereon. The wearable device may perform beamforming operations or other separation procedures to isolate the external signal and the self-voice signal from the input audio signal. The wearable device may apply a first filter to the external signal, and a second filter to the self-voice signal. The wearable device may then mix the filtered signals, and generate an output signal that sounds natural to the user.
    Type: Grant
    Filed: February 26, 2019
    Date of Patent: June 9, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Lae-Hoon Kim, Dongmei Wang, Fatemeh Saki, Taher Shahbazi Mirzahasanloo, Erik Visser, Rogerio Guedes Alves
  • Patent number: 10586546
    Abstract: An example apparatus includes a memory configured to store the audio data; and one or more processors in communication with the memory, the one or more processors configured to: decode, from an encoded audio bitstream, a unique identifier for each of a plurality of subbands of audio data; perform inverse pyramid vector quantization (PVQ) using a compact map to reconstruct a residual vector for each subband of the plurality of subbands of the audio data based on the unique identifier for the respective subband of the plurality of subbands of the audio data, wherein the compact map is generated using structural unification of vectors across subbands and relational compression, and wherein the unique identifiers correspond to codevectors; and reconstruct, based on the residual vectors and energy scalars for each subband, the plurality of subbands of the audio data.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: March 10, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Taher Shahbazi Mirzahasanloo, Walter Andres Zuluaga, Rogerio Guedes Alves
  • Patent number: 10573331
    Abstract: An example apparatus includes a memory configured to store the audio data; and one or more processors in communication with the memory, the one or more processors configured to: obtain, for each of a plurality of subbands of audio data, a respective energy scalar and a respective residual identifier; determine overall distortion levels for a plurality of candidate subband pulse allocations for performing pyramid vector dequantization (PVdQ) of the residual identifiers; select, from the plurality of subband pulse allocations and based on the overall distortion levels, a candidate subband pulse allocation; and perform, using the candidate subband pulse allocation, PVdQ on the residual identifiers to reconstruct a residual vector for each subband.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: February 25, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves
  • Patent number: 10559315
    Abstract: A method of encoding audio data includes determining an energy level of a first subband of frequency domain audio data, determining a bit allocation for a coarse quantization process and a fine quantization process, determining that the energy level of the first subband of frequency domain audio data is outside a predetermined range of energy levels for the coarse quantization process, reallocating bits assigned to the fine quantization process to an extended-range coarse quantization process, the extended-range coarse quantization process using an extended range of energy levels, wherein the extended range of energy levels is larger than the predetermined range of energy levels for the coarse quantization process, and quantizing the energy level of the first subband of frequency domain audio data using the extended-range coarse quantization process to produce a quantized extended-range coarse energy level.
    Type: Grant
    Filed: July 25, 2018
    Date of Patent: February 11, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves
  • Publication number: 20190371349
    Abstract: In general, techniques are described by which to perform audio coding based on audio pattern recognition. A source device comprising a memory and a processor may be configured to perform the techniques. The memory may store audio data. The processor may obtain, from a plurality of categories, a category to which the audio data corresponds, and obtain, based on the category, a set of pyramid vector quantization (PVQ) parameters from a plurality of sets of PVQ parameters. The processor may also perform, based on the set of PVQ parameters, PVQ with respect to the audio data to obtain a residual identifier representative of the audio data, and specify, in the bitstream, the residual identifier.
    Type: Application
    Filed: July 31, 2018
    Publication date: December 5, 2019
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves
  • Publication number: 20190371347
    Abstract: In general, this disclosure describes techniques for seamless audio data compression control system that can respond to the increasing adaptation demands for source coding characteristics to accommodate co-existence of various devices in a personal area network. In one example, a source device includes a memory and one or more processors in communication with the memory. The memory is configured to store audio data. The one or more processors are configured to select, based on a nominal compression ratio or a streaming rate, a compression level of multiple compression levels, the multiple compression levels arranged hierarchically to allow for dynamic transitioning between the compression levels. The one or more processors are further configured to encode, based on the selected compression level of the multiple compression levels, the audio data stored to the memory.
    Type: Application
    Filed: July 31, 2018
    Publication date: December 5, 2019
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves
  • Publication number: 20190341064
    Abstract: An example apparatus includes a memory configured to store the audio data; and one or more processors in communication with the memory, the one or more processors configured to: obtain, for each of a plurality of subbands of audio data, a respective energy scalar and a respective residual identifier; determine overall distortion levels for a plurality of candidate subband pulse allocations for performing pyramid vector dequantization (PVdQ) of the residual identifiers; select, from the plurality of subband pulse allocations and based on the overall distortion levels, a candidate subband pulse allocation; and perform, using the candidate subband pulse allocation, PVdQ on the residual identifers to reconstruct a residual vector for each subband.
    Type: Application
    Filed: July 31, 2018
    Publication date: November 7, 2019
    Inventors: Taher Shahbazi Mirzahasanloo, Rogerio Guedes Alves