Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

318 results about "Frequency matching" patented technology

Abstract. Frequency matching is a sampling design used in case–control studies to assure that cases and controls have the same distributions over strata defined by matching factors. Frequency matching is also used in cohort studies to insure that exposed and unexposed individuals have the same distributions over strata defined by known risk factors.

Method for extracting fault features of rotating mechanical equipment

The invention provides a method for extracting the fault features of rotating mechanical equipment, which comprises the following steps: (1) carrying out equal-time-interval sampling on a vibration signal and carrying out time domain processing, and extracting time domain features; (2) carrying out envelope detection processing on an equal-time-interval sampling vibration signal x(n) so as to obtain an equal-time-interval sampling envelope signal, and extracting the features of the envelope signal; (3) reconstituting an equal-angle-interval sampling envelope signal y(n) by using the equal-time-interval sampling envelope signal and rotating speed information; (4) carrying out equal-angle moving average filter processing on the equal-angle-interval sampling envelope signal y(n) so as to obtain a signal z (n); and (5) solving the Fourier transform of the signal z (n), seeking feature frequencies by using a feature frequency matching method, and extracting the fault features of a frequency domain. The method not only can suppress interferences under the condition that the resolution ratio of a frequency domain is not reduced, but also can extract actual feature frequencies under the condition that rotating speeds and mechanical parts have deviations, and therefore, smaller potential faults can be effectively found.
Owner:北京昊鹏智能技术有限公司

Tinnitus detecting method and tinnitus therapeutic apparatus

The invention provides a tinnitus detecting method and a tinnitus therapeutic apparatus. The method includes the steps of conducting pure tone threshold detection of two ears, selecting the tested ear according to the result of the pure tone threshold detection, conducting tinnitus frequency matching of the tinnitus ear through a three-point forced choice method to obtain the tinnitus frequency, and conducting tinnitus loudness matching of the tinnitus ear with the tinnitus frequency as the datum to obtain a tinnitus perception threshold. By means of a sound stimulation strategy, the tinnitus therapeutic apparatus comprises a computer readable medium, a detection control unit, a treatment control unit, a headset and a feedback unit. The detection control unit is used for conducting tinnitus detection and involves pure tone threshold detection, tinnitus frequency matching and tinnitus loudness matching. The treatment control unit processes audio files for treatment according to the result of the tinnitus detection, and therefore the individual treatment scheme is obtained. By means of the method and the apparatus, the tinnitus detection time is shortened, and the fault tolerance capacity is improved; by means of the tinnitus therapeutic apparatus, diagnosis and treatment are integrated, the treatment efficiency is improved, and the treatment cost is reduced.
Owner:FOSHAN BOZHI MEDICAL TECH CO LTD

Robust voice recognition method based on acoustic model array

ActiveCN104392718AMinimize the impact of adaptationHigh precisionSpeech recognitionFeature vectorFeature extraction
The invention discloses a robust voice recognition method based on an acoustic model array. The robust voice recognition method comprises a training phase and a testing phase. At the training phase, a plurality of upper limiting frequencies are set for training voice according to the highest frequency of the voice, a plurality of groups of characteristic vectors are extracted and model training is performed to obtain the acoustic model array. At the testing phase, firstly, the upper limiting frequency of test voice is estimated according to a small quantity of self-adaptive voice in the testing environment; secondly, an acoustic model matched with the upper limiting frequency of the test voice is selected from the acoustic model array, and the parameters of the acoustic model are adjusted to obtain a testing environment acoustic model; finally, characteristic extraction is performed according to the upper limiting frequency of the test voice so as to obtain a characteristic vector of the noise-containing test voice, and acoustic decoding is performed on the characteristic vector by use of the testing environment acoustic model to obtain an identification result. The robust voice recognition method based on the acoustic model array is capable of improving the performance of a voice recognition system in a noise environment and improving the robustness of the system.
Owner:HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products