Raghavendra S Prabhu, Age 47231 S Juanita Ave #A, Redondo Beach, CA 90277

7003093, Feb 21, 2006

Aug 23, 2001

09/938699

Raghavendra S. Prabhu - Costa Mesa CA, US
Adam Strauss - Brea CA, US
Stan Hsieh - Diamond Bar CA, US
Zhen Zhu - Irvine CA, US
Anurag Bist - Irvine CA, US

Intel Corporation - Santa Clara CA

H04M 1/00
H04M 3/00

37939002, 379386, 379282, 379283, 379351, 379284

Disclosed is an integrated tone detection processor for discriminating between tone and voice signals and determining the tones. The tone detection processor performs Automatic Gain Control (AGC) to normalize the power of the tone or voice signal. Further, the energy of the tone or voice signals are determined at specific frequencies utilizing a Goertzel Filter process. The tone detection processor determines whether or not a tone is present, and if a tone exists, determines the type of tone. Based upon determining the two maximum energy levels of the Goertzel filtered tone, whether the tone is a single tone, dual tone, silence, or other (e. g. speech) can be discriminated. The tone can then be identified by a user-defined dictionary of tones. Based upon various ON and OFF cadence checks in combination with the use of TONE ON and TONE OFF counters, tones can be declared.

8515335, Aug 20, 2013

Nov 30, 2009

12/627875

Philip Anthony Dafesh - Manhattan Beach CA, US
Raghavendra S. Prabhu - Los Angeles CA, US
Esteban Luis Valles - Los Angeles CA, US

The Aerospace Corporation - El Segundo CA

H04K 3/00
H04B 17/00
H04M 11/00
H04W 4/00

455 1, 455 6711, 4554261, 455403, 4554221

Cognitive anti-jam receiver systems and associated methods are provided. The systems and methods may include a signal analysis module that processes a baseband signal to determine one or more signal characteristics of the baseband signal, the baseband signal comprising at least a desired signal; a cognitive decision unit that receives the one or more signal characteristics from the signal analysis module, and generates at least one first adaptive parameter; and at least one anti-jam processing module that processes the baseband signal to generate a modified signal that reduces an impact of at least one jammer signal on a quality of reception of the desired signal from the baseband signal, where processing by the at least one anti-jam processing module may be based at least in part on the received at least one first adaptive parameter from the cognitive decision unit.

2002006, May 30, 2002

Sep 6, 2001

09/948501

Anurag Bist - Newport Coast CA, US
Stan Hsieh - Diamond Bar CA, US
Raghavendra Prabhu - Costa Mesa CA, US
Zhen Zhu - Irvine CA, US
Adam Strauss - Brea CA, US

H04B003/20

370/289000, 370/419000

A network echo canceller for integrated telecommunications processing. The network echo canceller processes echoes in multiple communication channels over a packet network. The network echo canceller adapts a least means squared finite impulse response filter to each communication channel in order to estimate an echo therein. The echo estimation is subtracted from signals that are being sent over each communication channel. The echo canceller includes a residual error suppressor to suppress non-linear sources of echo when desired. The echo canceller includes a double talk detector to inhibit filter adaptation during double talk. The network echo canceller is programmable into a digital signal processor and can be flexibly controlled through messaging.

2002011, Aug 22, 2002

Aug 23, 2001

09/938104

Adam Strauss - Brea CA, US
Anurag Bist - Irvine CA, US
Stan Hsieh - Diamond Bar CA, US
Zhen Zhu - Irvine CA, US
Raghavendra Prabhu - Costa Mesa CA, US

G10L015/20
G10L015/00

704/233000

Disclosed is an integrated voice activation detector for detecting whether voice is present. In one embodiment, the integrated voice activation detector includes a semiconductor integrated circuit having at least one signal processing unit to perform voice detection and a storage device to store signal processing instructions for execution by the at least one signal processing unit to: detect whether noise is present to determine whether a noise flag should be set, detect a predetermined number of zero crossings to determine whether a zero crossing flag should be set, detect whether a threshold amount of energy is present to determine whether an energy flag should be set, and detect whether instantaneous energy is present to determine whether an instantaneous energy flag should be set. Utilizing a combination of the noise, zero crossing, energy, and instantaneous energy flags the integrated voice activation detector determines whether voice is present.

2023001, Jan 19, 2023

Aug 29, 2022

17/823011

- Cupertino CA, US
Andrew E. Greenwood - San Francisco CA, US
Baptiste P. Paquier - Saratoga CA, US
Hanchi Chen - San Jose CA, US
Raghavendra S. Prabhu - Redondo Beach CA, US

H04R 1/10
H04R 3/04

A method performed by an in-ear headphone. Coupled to the in-ear headphone is a first ear tip that is inserted into an ear canal of a user. The method obtains an audio signal from an audio source device paired with the in-ear headphone and uses the signal to drive a speaker of the headphone to output a sound into the ear canal. The method obtains a microphone signal that is responsive to the outputted sound. The method notifies the user to replace the first ear tip with a second ear tip in response to a parameter associated with the microphone signal being less than a threshold.

2021001, Jan 14, 2021

Jul 1, 2020

16/918950

- Cupertino CA, US
Andrew E. Greenwood - San Francisco CA, US
Baptiste P. Paquier - Saratoga CA, US
Hanchi Chen - San Jose CA, US
Raghavendra S. Prabhu - Redondo Beach CA, US

H04R 1/10
H04R 3/04

A method performed by an in-ear headphone. Coupled to the in-ear headphone is a first ear tip that is inserted into an ear canal of a user. The method obtains an audio signal from an audio source device paired with the in-ear headphone and uses the signal to drive a speaker of the headphone to output a sound into the ear canal. The method obtains a microphone signal that is responsive to the outputted sound. The method notifies the user to replace the first ear tip with a second ear tip in response to a parameter associated with the microphone signal being less than a threshold.

2018003, Feb 1, 2018

Aug 1, 2016

15/225595

- Cupertino CA, US
Vasu Iyengar - Pleasanton CA, US
Sarmad Aziz Malik - Cupertino CA, US
Raghavendra Prabhu - Culver City CA, US

G10L 25/30
G10L 25/72
G10L 21/0232
G10L 25/84
G10L 21/028

Method of speech enhancement using Neural Network-based combined signal starts with training neural network offline which includes: (i) exciting at least one accelerometer and at least one microphone using training accelerometer signal and training acoustic signal, respectively. The training accelerometer signal and the training acoustic signal are correlated during clean speech segments. Training neural network offline further includes (ii) selecting speech included in the training accelerometer signal and in the training acoustic signal, and (iii) spatially localizing the speech by setting a weight parameter in the neural network based on the selected speech included in the training accelerometer signal and in the training acoustic signal. The neural network that is trained offline is then used to generate a speech reference signal based on an accelerometer signal from the at least one accelerometer and an acoustic signal received from the at least one microphone. Other embodiments are described.

2015011, Apr 23, 2015

Oct 17, 2014

14/517700

- Cupertino CA, US
Jason Wung - Los Angeles CA, US
Joshua Atkins - Pacific Palisades CA, US
Raghavendra Prabhu - Redondo Beach CA, US

G10L 21/0208
G10L 15/20

704233

An echo canceller can be arranged to receive an input signal and to receive a reference signal. The echo canceller can subtract a linear component of the reference signal from the input signal. A noise suppressor can suppress non-linear effects of the reference signal in the input signal in correspondence with a large number of selectable parameters. Such suppression can be provided on a frequency-by-frequency basis, with a unique set of tunable parameters selected for each frequency. A degree of suppression provided by the noise suppressor can correspond to an estimate of residual echo remaining after the one or more linear components of the reference signal have been subtracted from the input signal, to an estimated double-talk probability, and to an estimated signal-to-noise ratio of near-end speech in the input signal for each respective frequency. A speech recognizer can receive a processed input signal from the noise suppressor.