P

Inventor

HERMANSKY HYNEK

CH13 patents
⚠️ This page may combine multiple inventors who share the name “HERMANSKY HYNEK”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

US WEST ADVANCED TECH INC

3 patents
US5537647AJul 16, 1996

Noise resistant auditory model for parametrization of speech

US WEST ADVANCED TECH INC195 citations98
US5450522ASep 12, 1995

Auditory model for parametrization of speech

US WEST ADVANCED TECH INC72 citations93
US5165008ANov 17, 1992

Speech synthesis using perceptual linear prediction parameters

US WEST ADVANCED TECH INC47 citations92

OREGON GRADUATE INST SCIENCE

2 patents
US6098038AAug 1, 2000

Method and system for adaptive speech enhancement using frequency specific signal-to-noise ratio estimates

OREGON GRADUATE INST SCIENCE90 citations97
US5878389AMar 2, 1999

Method and system for generating an estimated clean speech signal from a noisy speech signal

OREGON GRADUATE INST SCIENCE51 citations90

GARUDADRI HARINATH

2 patents
US8428957B2Apr 23, 2013

Spectral noise shaping in audio coding based on spectral dynamics in frequency sub-bands

GARUDADRI HARINATH38 citations93
US8392176B2Mar 5, 2013

Processing of excitation in audio coding and decoding

GARUDADRI HARINATH12 citations82

QUALCOMM INC

2 patents
US7089178B2Aug 8, 2006

Multistream network feature processing for a distributed speech recognition system

QUALCOMM INC34 citations86
US8027242B2Sep 27, 2011

Signal coding and decoding based on spectral dynamics

QUALCOMM INC4 citations61

KINTZLEY KEITH

2 patents
US9799333B2Oct 24, 2017

System and method for processing speech to identify keywords or other information

KINTZLEY KEITH5 citations79
US9177547B2Nov 3, 2015

System and method for processing speech to identify keywords or other information

KINTZLEY KEITH4 citations68

INTERNAT COMP SCIENCE INST

1 patent
US7254538B1Aug 7, 2007

Nonlinear mapping for feature extraction in automatic speech recognition

INTERNAT COMP SCIENCE INST38 citations91

UNIV COLUMBIA

1 patent
US7672838B1Mar 2, 2010

Systems and methods for speech recognition using frequency domain linear prediction polynomials to form temporal and spectral envelopes from frequency domain representations of signals

UNIV COLUMBIA22 citations90