Patents by Inventor Vahid MONTAZERI
Vahid MONTAZERI 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).
-
Patent number: 11805360Abstract: A device includes a memory configured to store instructions and one or more processors configured to execute the instructions. The one or more processors are configured to execute the instructions to receive audio data including a first audio frame corresponding to a first output of a first microphone and a second audio frame 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 first noise-suppression network and a second noise-suppression network. The first noise-suppression network is configured to generate a first noise-suppressed audio frame and the second noise-suppression network is configured to generate a second noise-suppressed audio frame. The one or more processors are further configured to execute the instructions to provide the noise-suppressed audio frames to an attention-pooling network. The attention-pooling network is configured to generate an output noise-suppressed audio frame.Type: GrantFiled: July 21, 2021Date of Patent: October 31, 2023Assignee: QUALCOMM IncorporatedInventors: Vahid Montazeri, Van Nguyen, Hannes Pessentheiner, Lae-Hoon Kim, Erik Visser, Rogerio Guedes Alves
-
Publication number: 20230326477Abstract: A device to perform speech enhancement includes one or more processors configured to process image data to detect at least one of an emotion, a speaker characteristic, or a noise type. The one or more processors are also configured to generate context data based at least in part on the at least one of the emotion, the speaker characteristic, or the noise type. The one or more processors are further configured to obtain input spectral data based on an input signal. The input signal represents sound that includes speech. The one or more processors are also configured to process, using a multi-encoder transformer, the input spectral data and the context data to generate output spectral data that represents a speech enhanced version of the input signal.Type: ApplicationFiled: June 14, 2023Publication date: October 12, 2023Inventors: Kyungguen BYUN, Shuhua ZHANG, Lae-Hoon KIM, Erik VISSER, Sunkuk MOON, Vahid MONTAZERI
-
Patent number: 11715480Abstract: A device to perform speech enhancement includes one or more processors configured to obtain input spectral data based on an input signal. The input signal represents sound that includes speech. The one or more processors are also configured to process, using a multi-encoder transformer, the input spectral data and context data to generate output spectral data that represents a speech enhanced version of the input signal.Type: GrantFiled: March 23, 2021Date of Patent: August 1, 2023Assignee: QUALCOMM IncorporatedInventors: Kyungguen Byun, Shuhua Zhang, Lae-Hoon Kim, Erik Visser, Sunkuk Moon, Vahid Montazeri
-
Patent number: 11705147Abstract: Systems, methods and computer-readable media are provided for speech enhancement using a hybrid neural network. An example process can include receiving, by a first neural network portion of the hybrid neural network, audio data and reference data, the audio data including speech data, noise data, and echo data; filtering, by the first neural network portion, a portion of the audio data based on adapted coefficients of the first neural network portion, the portion of the audio data including the noise data and/or echo data; based on the filtering, generating, by the first neural network portion, filtered audio data including the speech data and an unfiltered portion of the noise data and/or echo data; and based on the filtered audio data and the reference data, extracting, by a second neural network portion of the hybrid neural network, the speech data from the filtered audio data.Type: GrantFiled: April 28, 2021Date of Patent: July 18, 2023Assignee: QUALCOMM IncorporatedInventors: Erik Visser, Vahid Montazeri, Shuhua Zhang, Lae-Hoon Kim
-
Patent number: 11676571Abstract: A device for speech generation includes one or more processors configured to receive one or more control parameters indicating target speech characteristics. The one or more processors are also configured to process, using a multi-encoder, an input representation of speech based on the one or more control parameters to generate encoded data corresponding to an audio signal that represents a version of the speech based on the target speech characteristics.Type: GrantFiled: January 21, 2021Date of Patent: June 13, 2023Assignee: QUALCOMM IncorporatedInventors: Kyungguen Byun, Sunkuk Moon, Shuhua Zhang, Vahid Montazeri, Lae-Hoon Kim, Erik Visser
-
Publication number: 20230026735Abstract: A device includes a memory configured to store instructions and one or more processors configured to execute the instructions. The one or more processors are configured to execute the instructions to receive audio data including a first audio frame corresponding to a first output of a first microphone and a second audio frame 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 first noise-suppression network and a second noise-suppression network. The first noise-suppression network is configured to generate a first noise-suppressed audio frame and the second noise-suppression network is configured to generate a second noise-suppressed audio frame. The one or more processors are further configured to execute the instructions to provide the noise-suppressed audio frames to an attention-pooling network. The attention-pooling network is configured to generate an output noise-suppressed audio frame.Type: ApplicationFiled: July 21, 2021Publication date: January 26, 2023Inventors: Vahid MONTAZERI, Van NGUYEN, Hannes PESSENTHEINER, Lae-Hoon KIM, Erik VISSER, Rogerio Guedes ALVES
-
Publication number: 20220310108Abstract: A device to perform speech enhancement includes one or more processors configured to obtain input spectral data based on an input signal. The input signal represents sound that includes speech. The one or more processors are also configured to process, using a multi-encoder transformer, the input spectral data and context data to generate output spectral data that represents a speech enhanced version of the input signal.Type: ApplicationFiled: March 23, 2021Publication date: September 29, 2022Inventors: Kyungguen BYUN, Shuhua ZHANG, Lae-Hoon KIM, Erik VISSER, Sunkuk MOON, Vahid MONTAZERI
-
Publication number: 20220230623Abstract: A device for speech generation includes one or more processors configured to receive one or more control parameters indicating target speech characteristics. The one or more processors are also configured to process, using a multi-encoder, an input representation of speech based on the one or more control parameters to generate encoded data corresponding to an audio signal that represents a version of the speech based on the target speech characteristics.Type: ApplicationFiled: January 21, 2021Publication date: July 21, 2022Applicant: QUALCOMM IncorporatedInventors: Kyungguen BYUN, Sunkuk MOON, Shuhua ZHANG, Vahid MONTAZERI, Lae-Hoon KIM, Erik VISSER
-
Publication number: 20210343306Abstract: Systems, methods and computer-readable media are provided for speech enhancement using a hybrid neural network. An example process can include receiving, by a first neural network portion of the hybrid neural network, audio data and reference data, the audio data including speech data, noise data, and echo data; filtering, by the first neural network portion, a portion of the audio data based on adapted coefficients of the first neural network portion, the portion of the audio data including the noise data and/or echo data; based on the filtering, generating, by the first neural network portion, filtered audio data including the speech data and an unfiltered portion of the noise data and/or echo data; and based on the filtered audio data and the reference data, extracting, by a second neural network portion of the hybrid neural network, the speech data from the filtered audio data.Type: ApplicationFiled: April 28, 2021Publication date: November 4, 2021Inventors: Erik VISSER, Vahid MONTAZERI, Shuhua ZHANG, Lae-Hoon KIM