196 results about "Reference tone" patented technology

An image processing apparatus adapted to perform tone correction of luminance of an image, comprises: a image dividing unit configured to divide the image into a plurality of blocks; a calculation unit configured to calculate a plurality of feature amounts of each of the blocks including a luminance value and calculate a saturated feature amount based on the plurality of calculated feature amounts, wherein the saturated feature amount represents color deviation tendency when the tone correction is applied to the image using a reference tone correction characteristic; a changing unit configured to change the reference tone correction characteristic according to the calculated saturated feature amount; and a correction unit configured to perform the tone correction based on the changed reference tone correction, wherein the changing unit weakens a degree of the reference tone correction characteristic when the saturated feature amount indicates a stronger tendency toward color deviation.

Techniques for evaluating the audio quality of an audio test signal are disclosed. These techniques provide a quality analysis that takes into account spatial audio distortions between the audio test signal and a reference audio signal. These techniques involve, for example, determining a plurality of audio spatial cues for an audio test signal, determining a corresponding plurality of audio spatial cues for an audio reference signal, comparing the determined audio spatial cues of the audio test signal to the audio spatial cues of the audio reference signal, and determining the audio quality of the audio test signal.

The invention provides a non-reference tone mapping image quality evaluation method based on multi-feature fusion. The method mainly comprises a feature extraction stage and a training regression stage. In the feature extraction stage, features of an image are extracted in three fields, and entropy features of the image, texture features based on a gray level co-occurrence matrix and natural scenestatistical features are extracted in the pixel field. In the field of ambiguity, local phase consistency is adopted to evaluate the overall ambiguity, and small block features are extracted from anedge region to measure the halo effect. In the color field, an image is converted into an opposite color space, and overall color information and contrast information of all channels are measured. Finally, the quality of the tone mapping image is predicted by using a machine learning method. The algorithm provided by the invention can accurately and effectively predict the quality of the tone mapping image.

For each one note or for each plurality of notes constituting a reference tone, a segment setting section segments a time series of actual pitches of the reference tone into one or more note segments. For each of the one or more note segments, a relativization section creates a time series of relative pitches that are relative values of individual ones of the actual pitches of the reference tone to a normal pitch of the note of the note segment. Information registration section stores, into a storage device, relative pitch information comprising the time series of relative pitches of each individual one of the note segments. The segment setting section may use musical score data, time-serially designating the notes of the reference tone, to set each of the note segments for each note designated by the musical score data, and may correct at least one of start and end points of each of the set note segments in response to user's operation.

A method of calibrating an earphone may include: securing an ANC earphone to a calibration fixture, the calibration fixture including an ear model configured to support the ANC earphone, the ear model having an ear canal configured to anatomically resemble a human ear canal and a concha configured to anatomically resemble a human ear concha, the ear canal extending from the concha to an inner end of the ear canal; generating, with the ANC earphone, an audio signal based on a reference tone; determining a characteristic of the audio signal; comparing the characteristic of the audio signal to a previously determined reference characteristic; and adjusting a gain value of the ANC earphone based on the comparing. Additional methods and apparatus are also disclosed.

A tone compensation method for a color printer and a color printer having a tone compensator are provided, wherein the method includes the steps of (a) acquiring a reference tone reproduction curve of print colors based on a printing environment, (b) forming sample patterns for one or more colors on a predetermined object medium, (c) forming a sectional tone reproduction curve by using the sample patterns, and (d), adjusting one or more print variables to compensate the sectional tone reproduction curve in order to reduce sectional errors between the reference tone reproduction curve and the sectional tone reproduction curve. Accordingly, it is possible to provide a tone compensation method capable of compensating for a sectional tone reproduction curve to approximate a reference tone reproduction curve without complicated mathematical calculations, and which is substantially unaffected by external disturbances and noise.

An audio processing device for use in a network connected audio conferencing system is provided, comprising: a network microphone array comprising two or more microphones (mics) and a beamforming circuit, wherein the network mic array is adapted to acquire acoustic audio signals, convert the same to electric audio signals, perform audio beamforming on the electric audio signals, and output a digital combined beamforming circuit output signal that comprises a first signal part and a second signal part, and wherein the first signal part comprises a first set of digital bits that comprises an active beam index, and wherein the active beam index encodes a selected beam position out of a possible N beam positions, and wherein the second signal part comprises a second set of digital bits that comprises a beamformed audio signal; a receiver adapted to receive the digital combined beamforming circuit output signal and split the same into the first signal part and the second signal part; a plurality of acoustic echo cancellation filter devices, each of which are adapted to receive the second signal part and a far end reference audio signal from a far end audio processing device, and perform acoustic echo cancellation on the beamformed audio signal in view of the far end audio signal; and an AEC filter circuit controller adapted to receive the first signal part, decipher the active beam index encoded in the first beamformed audio signal part to determine which of the N beam positions is active, and select a corresponding one of the plurality of acoustic echo cancellation filter devices based on the active one of N beam positions to generate an output audio signal from the audio processing device to be transmitted to the far end audio processing device.

Image processing is carried out accurately on image data obtained by a digital camera, for a high-quality reproduced image. Image data S0 is read and main part information M is acquired. Scene information H is obtained by inferring a photography scene based on the main part information M and photography information T added to the image data S0. A tone processing condition K0 corresponding to the scene information H is read from a memory 24 and a tone processing condition K1 is set by correcting a reference tone processing condition B according to the tone processing condition K0. Image processing is carried out on the image data S0 according to the tone processing condition K1 and image processing conditions G, and processed image data S1 is generated.

The invention belongs to the field of image processing and provides a reference-free tone mapping image quality evaluation method based on color statistics and information entropy. According to the method, the technical proposal adopted by the invention is that an image quality evaluation method without reference tone mapping based on color statistics and information entropy is provided. The method comprises the following steps: first, data preparation; 2, extract color statistical features, mainly comprise that following three steps: (1) decomposing color channel; 2) carry out division normalization operation on that channels in (1) to obtain respective color normalization coefficient; (3) parameter fitting; 3, feature extraction of information entropy; Step 4, quality prediction. Featureextraction of the test set, input to the trained model, predict the quality of the test chart score. The invention is mainly applied to image processing occasions.

Disclosed is a method and apparatus for optically modulating and transmitting source data. An optical comb comprising optical tones having a frequency spacing equal to Δf is generated by an optical comb generator. Selected ones of the optical tones in the optical comb are modulated according to the source data to produce a comb of modulated optical tones. At least one optical tone in the optical comb is frequency shifted by a frequency less than Δf to produce a frequency shifted unmodulated optical reference tone. The optical comb, the frequency shifted unmodulated optical reference tone and the comb of modulated tones are multiplexed onto at least one optical path.

The invention discloses a speech synthesis method, electronic equipment and a storage device, and the method comprises the steps: obtaining a to-be-synthesized text and a target emotion type of the to-be-synthesized text, and obtaining a reference audio of the target emotion type; based on the data distribution condition of the reference audio about the rhythm parameters, obtaining rhythm features corresponding to the target emotion type; wherein the rhythm parameters comprise at least one of the following parameters: fundamental frequency, intensity and duration; performing feature extraction on the phoneme sequence of the to-be-synthesized text to obtain phoneme features of the to-be-synthesized text; and decoding by utilizing the rhythm features and the phoneme features to obtain a synthesized audio after the to-be-synthesized text is fused into the target emotion type. According to the scheme, the emotion can be accurately fused into the synthesized audio.

The invention discloses an audio processing method and device, electronic equipment and a storage medium. The audio processing method is applied to the electronic equipment, and the electronic equipment comprises a loudspeaker, a first microphone and a second microphone, wherein the first microphone is arranged outside a cavity of a box body corresponding to the loudspeaker, and the second microphone is arranged in the cavity of the box body. The audio processing method comprises the following steps: controlling the loudspeaker to play an audio signal to be played; acquiring a first audio signal acquired by the first microphone when the loudspeaker plays the audio signal to be played; acquiring a second audio signal acquired by the second microphone when the loudspeaker plays the audio signal to be played, and taking the second audio signal as a reference audio signal for echo cancellation; and performing echo cancellation on the first audio signal according to the obtained reference audio signal to obtain a third audio signal after echo cancellation. According to the method, the echoes in the sounds collected by the microphone can be well eliminated.

The invention relates to the technical field of audios, and provides a transient noise detection method. The method comprises the following steps of acquiring an audio frame signal with a preset duration; performing wavelet decomposition on the first audio frame signal to obtain a first wavelet decomposition signal corresponding to the first audio frame signal, wherein the first wavelet decomposition signal comprises a plurality of sub-wavelet decomposition signals; determining first reference audio intensity values of the first sub-wavelet decomposition signals according to reference audio intensity values of all sample points in the first sub-wavelet decomposition signals; determining energy distribution information of the first wavelet decomposition signal according to first reference audio intensity values of all the sub-wavelet decomposition signals in the first wavelet decomposition signal; and determining a probability that the first audio frame signal is a transient noise according to the energy distribution information of the first wavelet decomposition signal. By implementing the embodiment, the sample points in the wavelet packet decomposition signal are counted, so thatthe accuracy of transient noise detection is improved.

The invention discloses an echo elimination method. An existing method only adopts an acoustic echo canceller, the echo cannot be completely eliminated, and the output of the acoustic echo canceller has an echo residue. According to the method, a low-pass filter, a loudspeaker, an acoustic echo canceller, a microphone and a high-pass filter, an energy extraction module, an energy comparison module, a comfort noise generation module and a near-end voice signal generation module are adopted. Firstly, the voice needing to be played is filtered, and the filtered voice is used as a reference tone;the reference tone is played; double-talk judgment is carried out on the high-frequency energy of the microphone; and according to the double-talk state, different processing is carried out on the residual signals. According to the method, low-echo and relatively high-keeping near-talk voice quality is achieved at the same time. According to the method, the implementation scheme is simple, the calculation amount is low, low echo residue can be realized in low-calculation-force embedded equipment, and relatively high near-talk voice quality can be kept.

The invention discloses an end-to-end accent conversion method, and belongs to the technical field of voice processing. The method converts a non-standard accent into a standard accent, and can be used for converting the voice of a patient with pronunciation disorder into standard voice. An accent conversion system for realizing the accent conversion method comprises a voice recognition module, aspeaker encoder, a voice synthesis module and a neural network vocoder, wherein the voice recognition module is used for adjusting the acoustic characteristics of input non-standard accent into the signal parameters of a standard accent, wherein the signal parameters are only related to the speaking content of the non-standard accent; and inputting the signal parameters of the non-standard accentand the speaker vector into the voice synthesis module, and synthesizing the standard accent of the specific speaker through the neural network vocoder after the voice is processed by the voice synthesis module. The method has the advantages that in the conversion process, the non-standard accent can be converted into the standard accent without any guidance of standard accent reference audios, and the original tone of a speaker is kept.

The embodiment of the invention discloses an audio stream processing method and a mobile terminal. The method comprises the steps of determining a target application corresponding to system time according to pre-stored mapping relationships between sound effect setting periods and the applications of the mobile terminal when it is detected that the system time of the mobile terminal is in a preset sound effect setting period; loading reference sound effect parameters corresponding to the target application in the operation memory of the mobile terminal; judging whether the application for playing the audio streams is the target application or not when a playing control instruction for audio streams is detected in the preset sound effect setting period; and reading the reference sound effect parameters from the operation memory if the application is the target application, configuring the sound effect parameters of the audio streams as the reference sound effect parameters, and playing the audio streams. According to the method and the mobile terminal provided by the embodiment of the invention, the fluency of playing the audio streams by the mobile terminal is improved, the memory resource management is optimized, and the user experience is improved.

The invention provides an audio recommendation method and device, electronic equipment and a computer storage medium, and relates to the technical field of artificial intelligence. According to the embodiment of the invention, in response to a page display request triggered by a target account, the reference audio corresponding to the target account is acquired according to the historical behaviordata of the target account, and at least one to-be-recommended audio is screened out from the candidate audio set according to the sound spectrum information of the reference audio and the sound spectrum information of each candidate audio in the candidate audio set, and the at least one screened to-be-recommended audio to a target account is recommended, according to the embodiment of the invention, the reference audio needs to be determined according to the historical behaviors of the user, and the to-be-recommended audio is screened from the candidate audio set according to the determinedreference audio, so that different audios can be flexibly recommended to the account for different accounts, thereby realizing personalized recommendation of the audios, and improving the user experience. Moreover, the historical behaviors of the target account and the content of the audio are considered at the same time, so that the accuracy of recommending the to-be-recommended audio to the target account is improved.

The embodiment of the invention discloses an audio beat information detection method and device and a storage medium, and the method comprises the steps: obtaining a to-be-detected audio, and obtaining the audio features of the to-be-detected audio; obtaining a pre-trained reference neural network model and a plurality of genre neural network models; respectively inputting the audio features of the to-be-detected audio into each genre neural network model to obtain a plurality of genre audio beat information; inputting the audio features of the to-be-detected audio into the reference neural network model to obtain reference audio beat information; and determining target audio beat information of the to-be-detected audio in combination with the reference audio beat information and the plurality of genre audio beat information. Therefore, multi-model training is carried out according to different audio genre styles, the target audio beat information output by the genre neural network model matched with the audio genre style of the to-be-detected audio is intelligently selected, and the detection accuracy of the audio beat information is improved.

The invention discloses a no-reference tone mapping image quality evaluation algorithm based on clustering perception, which comprises the following steps of: A, extracting clustering perception characteristics, namely respectively extracting two characteristics of area ratio and information entropy; B, extracting salient region features, namely extracting two features of block proportion and information entropy; C, extracting naturalness features, wherein the naturalness feature extraction comprises brightness statistical features and color channel statistical features; and step D, performingregression on all the features by using a machine learning method, so that an image quality evaluation score can be obtained. Compared with the prior art, the algorithm has the beneficial effects that a reference image is not needed when the test image is evaluated; a partitioning result of K-means clustering is improved, so that the precision of the algorithm is improved; the matrix non-negativedecomposition speed is high, and the detection method has a very good operation speed; the naturalness characteristics are combined with the brightness naturalness and the color naturalness, and theSROCC performance of the algorithm is greatly improved compared with single naturalness.