Patents by Inventor Tenkasi V. Ramabadran
Tenkasi V. Ramabadran 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: 11735175Abstract: A disclosed method includes monitoring an audio signal energy level while having a noise suppressor deactivated to conserve battery power, buffering the audio signal in response to a detected increase in the audio energy level, activating and running a voice activity detector on the audio signal in response to the detected increase in the audio energy level and activating and running a noise estimator in response to voice being detected in the audio signal by the voice activity detector. The method may further include activating and running the noise suppressor only if the noise estimator determines that noise suppression is required. The method activates and runs a noise type classifier to determine the noise type based on information received from the noise estimator and selects a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.Type: GrantFiled: January 7, 2021Date of Patent: August 22, 2023Assignee: Google LLCInventors: Plamen A. Ivanov, Kevin J. Bastyr, Joel A. Clark, Mark A. Jasiuk, Tenkasi V. Ramabadran, Jincheng Wu
-
Patent number: 11676581Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: GrantFiled: August 17, 2020Date of Patent: June 13, 2023Assignee: Google Technology Holdings LLCInventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Patent number: 11557308Abstract: An electronic device measures noise variability of background noise present in a sampled audio signal, and determines whether the measured noise variability is higher than a high threshold value or lower than a low threshold value. If the noise variability is determined to be higher than the high threshold value, the device categorizes the background noise as having a high degree of variability. If the noise variability is determined to be lower than the low threshold value, the device categorizes the background noise as having a low degree of variability. The high and low threshold values are between a high boundary point and a low boundary point. The high boundary point is based on an analysis of files including noises that exhibit a high degree of variability, and the low boundary point is based on an analysis of files including noises that exhibit a low degree of variability.Type: GrantFiled: December 21, 2020Date of Patent: January 17, 2023Assignee: Google LLCInventors: Mark A. Jasiuk, Tenkasi V. Ramabadran
-
Publication number: 20210125607Abstract: A disclosed method includes monitoring an audio signal energy level while having a noise suppressor deactivated to conserve battery power, buffering the audio signal in response to a detected increase in the audio energy level, activating and running a voice activity detector on the audio signal in response to the detected increase in the audio energy level and activating and running a noise estimator in response to voice being detected in the audio signal by the voice activity detector. The method may further include activating and running the noise suppressor only if the noise estimator determines that noise suppression is required. The method activates and runs a noise type classifier to determine the noise type based on information received from the noise estimator and selects a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.Type: ApplicationFiled: January 7, 2021Publication date: April 29, 2021Applicant: Google Technology Holdings LLCInventors: Plamen A. Ivanov, Kevin J. Bastyr, Joel A. Clark, Mark A. Jasiuk, Tenkasi V. Ramabadran, Jincheng Wu
-
Publication number: 20210110839Abstract: An electronic device measures noise variability of background noise present in a sampled audio signal, and determines whether the measured noise variability is higher than a high threshold value or lower than a low threshold value. If the noise variability is determined to be higher than the high threshold value, the device categorizes the background noise as having a high degree of variability. If the noise variability is determined to be lower than the low threshold value, the device categorizes the background noise as having a low degree of variability. The high and low threshold values are between a high boundary point and a low boundary point. The high boundary point is based on an analysis of files including noises that exhibit a high degree of variability, and the low boundary point is based on an analysis of files including noises that exhibit a low degree of variability.Type: ApplicationFiled: December 21, 2020Publication date: April 15, 2021Applicant: Google Technology Holdings LLCInventors: Mark A. Jasiuk, Tenkasi V. Ramabadran
-
Patent number: 10909977Abstract: A disclosed method includes monitoring an audio signal energy level while having a plurality of signal processing components deactivated and activating at least one signal processing component in response to a detected change in the audio signal energy level. The method may include activating and running a voice activity detector on the audio signal in response to the detected change where the voice activity detector is the at least one signal processing component. The method may further include activating and running the noise suppressor only if a noise estimator determines that noise suppression is required. The method may activate and runs a noise type classifier to determine the noise type based on information received from the noise estimator and may select a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.Type: GrantFiled: May 11, 2018Date of Patent: February 2, 2021Assignee: Google Technology Holdings LLCInventors: Plamen A. Ivanov, Kevin J. Bastyr, Joel A. Clark, Mark A. Jasiuk, Tenkasi V. Ramabadran, Jincheng Wu
-
Patent number: 10896685Abstract: An electronic device measures noise variability of background noise present in a sampled audio signal, and determines whether the measured noise variability is higher than a high threshold value or lower than a low threshold value. If the noise variability is determined to be higher than the high threshold value, the device categorizes the background noise as having a high degree of variability. If the noise variability is determined to be lower than the low threshold value, the device categorizes the background noise as having a low degree of variability. The high and low threshold values are between a high boundary point and a low boundary point. The high boundary point is based on an analysis of files including noises that exhibit a high degree of variability, and the low boundary point is based on an analysis of files including noises that exhibit a low degree of variability.Type: GrantFiled: August 23, 2017Date of Patent: January 19, 2021Assignee: Google Technology Holdings LLCInventors: Mark A. Jasiuk, Tenkasi V. Ramabadran
-
Publication number: 20200380961Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: ApplicationFiled: August 17, 2020Publication date: December 3, 2020Applicant: Google Technology Holdings LLCInventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Patent number: 10777190Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: GrantFiled: December 11, 2018Date of Patent: September 15, 2020Assignee: Google Technology Holdings LLCInventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Publication number: 20190122656Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: ApplicationFiled: December 11, 2018Publication date: April 25, 2019Inventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Patent number: 10229697Abstract: One method of operation includes beamforming a plurality of microphone outputs to obtain a plurality of virtual microphone audio channels. Each virtual microphone audio channel corresponds to a beamform. The virtual microphone audio channels include at least one voice channel and at least one noise channel. The method includes performing voice activity detection on the at least one voice channel and adjusting a corresponding voice beamform until voice activity detection indicates that voice is present on the at least one voice channel. Another method beamforms the plurality of microphone outputs to obtain a plurality of virtual microphone audio channels, where each virtual microphone audio channel corresponds to a beamform, and with at least one voice channel and at least one noise channel. The method performs voice recognition on the at least one voice channel and adjusts the corresponding voice beamform to improve a voice recognition confidence metric.Type: GrantFiled: July 31, 2013Date of Patent: March 12, 2019Assignee: Google Technology Holdings LLCInventors: Kevin J. Bastyr, Giles T Davis, Plamen A Ivanov, Rivanaldo S Oliveira, Tenkasi V Ramabadran, Snehitha Singaraju
-
Patent number: 10192548Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: GrantFiled: June 2, 2017Date of Patent: January 29, 2019Assignee: Google Technology Holdings LLCInventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Patent number: 10170105Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: GrantFiled: December 19, 2016Date of Patent: January 1, 2019Assignee: Google Technology Holdings LLCInventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Patent number: 10163438Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: GrantFiled: May 25, 2017Date of Patent: December 25, 2018Assignee: Google Technology Holdings LLCInventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Patent number: 10163439Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: GrantFiled: May 31, 2017Date of Patent: December 25, 2018Assignee: Google Technology Holdings LLCInventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Publication number: 20180268811Abstract: A disclosed method includes monitoring an audio signal energy level while having a plurality of signal processing components deactivated and activating at least one signal processing component in response to a detected change in the audio signal energy level. The method may include activating and running a voice activity detector on the audio signal in response to the detected change where the voice activity detector is the at least one signal processing component. The method may further include activating and running the noise suppressor only if a noise estimator determines that noise suppression is required. The method may activate and runs a noise type classifier to determine the noise type based on information received from the noise estimator and may select a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.Type: ApplicationFiled: May 11, 2018Publication date: September 20, 2018Inventors: Plamen A. Ivanov, Kevin J. Bastyr, Joel A. Clark, Mark A. Jasiuk, Tenkasi V. Ramabadran, Jincheng Wu
-
Publication number: 20170372721Abstract: An electronic device measures noise variability of background noise present in a sampled audio signal, and determines whether the measured noise variability is higher than a high threshold value or lower than a low threshold value. If the noise variability is determined to be higher than the high threshold value, the device categorizes the background noise as having a high degree of variability. If the noise variability is determined to be lower than the low threshold value, the device categorizes the background noise as having a low degree of variability. The high and low threshold values are between a high boundary point and a low boundary point. The high boundary point is based on an analysis of files including noises that exhibit a high degree of variability, and the low boundary point is based on an analysis of files including noises that exhibit a low degree of variability.Type: ApplicationFiled: August 23, 2017Publication date: December 28, 2017Inventors: Mark A. Jasiuk, Tenkasi V. Ramabadran
-
Publication number: 20170270913Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: ApplicationFiled: June 2, 2017Publication date: September 21, 2017Inventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Publication number: 20170270914Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: ApplicationFiled: June 5, 2017Publication date: September 21, 2017Inventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk
-
Publication number: 20170263243Abstract: An electronic device includes a microphone that receives an audio signal that includes a spoken trigger phrase, and a processor that is electrically coupled to the microphone. The processor measures characteristics of the audio signal, and determines, based on the measured characteristics, whether the spoken trigger phrase is acceptable for trigger phrase model training. If the spoken trigger phrase is determined not to be acceptable for trigger phrase model training, the processor rejects the trigger phrase for trigger phrase model training.Type: ApplicationFiled: May 25, 2017Publication date: September 14, 2017Inventors: Joel A. Clark, Tenkasi V. Ramabadran, Mark A. Jasiuk