6 results about "Music identification" patented technology

This invention relates to the field of music signal recognition technology, and more particularly to a method for recognizing the degree of music enjoyment based on music-EEG feature fusion. The method includes: extracting the Mel-frequency cepstral coefficients of the music signal; preprocessing and performing Fast Fourier Transform on the Mel-frequency cepstral coefficients to obtain the spectral feature values ​​of the music signal; and sequentially filtering, reducing dimensionality, and decorrelating the spectral feature values ​​of the music signal; extracting the Mel-frequency cepstral coefficients of the EEG signal; optimizing and updating the order of the Mel-frequency cepstral coefficients of the EEG signal so that the comprehensive error value between the EEG feature reconstruction signal and the original EEG signal meets a preset condition; aligning the music feature coefficients and the EEG feature reconstruction signal in the feature dimension and time axis using the FastDTW algorithm; and recognizing the degree of music enjoyment of the subject based on the alignment result. This invention effectively improves the robustness and accuracy of music recognition.

The invention provides a music time coding method for artificial neural network modeling. The method aims at the coding requirement of music beat time, molecules are decomposed according to a fixed denominator for multi-bit independent classification coding, and the method comprises the following steps: setting the fixed denominator as a composite number and decomposing the composite number into a prime factor combination; the molecules are mapped into vectors, the value range of each bit is determined by a cardinal number of a prime factor combination, and the vectors are converted into one-hot coding sub-vectors with redundant components removed. The technical scheme of the invention solves the problem that the traditional mean square error (MSE) ignores the internal correlation of scores and has high sparsity in the topology recognition task of an optical music recognition system (OMR), and compared with a traditional coding method adopting floating point numerical output and a mean square error loss function under the conditions of the same data set, model architecture and training hyper-parameters, the method provided by the invention has the advantages that the coding efficiency is greatly improved; according to the method, the comprehensive error index is reduced by about 21%, and the model precision and the training efficiency are improved.

The invention relates to the technical field of music recognition education, and discloses a music rhythm recognition and evaluation method and system based on multi-modal feedback. The music rhythm identification and evaluation method is applied to the music rhythm identification and evaluation electronic equipment, and specifically comprises the following steps: S101, receiving a music rhythm identification and evaluation request of a user side, and collecting time sequence data and force information of a pressing action of a user in real time through a sensor arranged in the music rhythm identification and evaluation electronic equipment, meanwhile, audio signals are collected and captured through a high-fidelity microphone or a direct audio interface. According to the method, objective quantitative evaluation of music rhythm capability is realized through a multi-modal data fusion analysis mechanism, three-modal synchronous acquisition and fusion analysis of time sequence data, strength information and audio signals are adopted, and a multi-level fusion strategy of a data level, a feature level and a decision level is adopted; an advanced algorithm combining dynamic time warping and a hidden Markov model overcomes the limitation of traditional single-mode evaluation.

A video editing method is performed by a computer device. The method includes: performing music recognition on audio data in first video data to obtain a recognition result of each of audio frames in the audio data, the recognition result indicating whether the audio frame belongs to a music audio frame; determining a music segment in the audio data based on the recognition results of the audio frames, the music segment comprising a plurality of music audio frames; and extracting, from the first video data, a video clip with a same playback period as the music segment as second video data comprising the music segment.

The application provides a vehicle-mounted music recognition method, which comprises the following steps: step 1, determining whether a command for starting music recognition is received; if yes, the next step is performed; otherwise, the current step is repeatedly performed; step 2, starting audio recording, recording current music with a preset time length, generating a recording file after pretreatment and saving the recording file in a cache; step 3, uploading the recording file to a server, receiving recognition information returned by the server and determining whether the current music is free to download according to the recognition information; if yes, step 5 is performed; otherwise, the next step is performed; step 4, determining whether a command for agreeing to pay for downloading is received; if yes, the server is accepted and the next step is performed; otherwise, step 7 is performed; step 5, downloading corresponding music and performing the next step; step 6, playing the downloaded music; and step 7, exiting the music recognition mode. The application improves the intelligent degree of vehicle-mounted music recognition.

A music recognition model training method executed by a computer device, comprising: acquiring a sample data set, in which each piece of sample data comprises a sample music clip and a sample music description corresponding thereto, the sample music description comprising a plurality of sample music attributes of the sample music clip (S201); and, on the basis of the sample data set, iteratively training a plurality of rounds a music recognition model to be trained (S202), the music recognition model comprising: a trained feature extraction sub-model and text recognition sub-model and a feature mapping sub-model to be trained, and each round of the iterative training comprising: using the feature extraction sub-model to extract a spectrum feature presented by the sample music clip (S2021); using the feature mapping sub-model to map the obtained spectrum feature to a description text feature, the description text feature being used for describing a plurality of training music attributes of the sample music clip (S2022); using the text recognition sub-model to recognize the description text feature so as to obtain a training music description (S2023); and, on the basis of the difference between the obtained training music description and the sample music description corresponding thereto, adjusting model parameters of the feature mapping sub-model (S2024).