摘要:
A portion of an audio signal is separated into multiple frames from which one or more different features are extracted. These different features are used, in combination with a set of rules, to classify the portion of the audio signal into one of multiple different classifications (for example, speech, non-speech, music, environment sound, silence, etc.). In one embodiment, these different features include one or more of line spectrum pairs (LSPs), a noise frame ratio, periodicity of particular bands, spectrum flux features, and energy distribution in one or more of the bands. The line spectrum pairs are also optionally used to segment the audio signal, identifying audio classification changes as well as speaker changes when the audio signal is speech.
摘要:
Digital image data is automatically processed by dividing stored image data into domain blocks and range blocks. The range blocks are subjected to processes such as a shrinking process to obtain mapped range blocks. The range blocks or domain blocks may also be processed by processes such as affine transforms. Then, for each domain block, the mapped range block which is most similar to the domain block is determined, and the address of that range block and the processes the blocks were subjected to are combined as an identifier which is appended to a list of identifiers for other domain blocks. The list of identifiers for all domain blocks is called a fractal transform and constitutes a compressed representation of the input image. To decompress the fractal transform and recover the input image, an arbitrary input image is formed into range blocks and the range blocks processed in a manner specified by the identifiers to form a representation of the original input image.
摘要:
A learning computer system may estimate unknown parameters and states of a stochastic or uncertain system having a probability structure. The system may include a data processing system that may include a hardware processor that has a configuration that: receives data; generates random, chaotic, fuzzy, or other numerical perturbations of the data, one or more of the states, or the probability structure; estimates observed and hidden states of the stochastic or uncertain system using the data, the generated perturbations, previous states of the stochastic or uncertain system, or estimated states of the stochastic or uncertain system; and causes perturbations or independent noise to be injected into the data, the states, or the stochastic or uncertain system so as to speed up training or learning of the probability structure and of the system parameters or the states.
摘要:
Disclosed is a method for predicting the spectral information of voice signals, including inputting the voice signals, performing morphological operations with the waveform image of the voice signals, extracting harmonic peaks as a result of the morphological operations, and predicting the spectral envelope information of the voice signals by interpolating the harmonic peaks.
摘要:
A portion of an audio signal is separated into multiple frames from which one or more different features are extracted. These different features are used, in combination with a set of rules, to classify the portion of the audio signal into one of multiple different classifications (for example, speech, non-speech, music, environment sound, silence, etc.). In one embodiment, these different features include one or more of line spectrum pairs (LSPs), a noise frame ratio, periodicity of particular bands, spectrum flux features, and energy distribution in one or more of the bands. The line spectrum pairs are also optionally used to segment the audio signal, identifying audio classification changes as well as speaker changes when the audio signal is speech.
摘要:
A portion of an audio signal is separated into multiple frames from which one or more different features are extracted. These different features are used, in combination with a set of rules, to classify the portion of the audio signal into one of multiple different classifications (for example, speech, non-speech, music, environment sound, silence, etc.). In one embodiment, these different features include one or more of line spectrum pairs (LSPs), a noise frame ratio, periodicity of particular bands, spectrum flux features, and energy distribution in one or more of the bands. The line spectrum pairs are also optionally used to segment the audio signal, identifying audio classification changes as well as speaker changes when the audio signal is speech.
摘要:
A portion of an audio signal is separated into multiple frames from which one or more different features are extracted. These different features are used, in combination with a set of rules, to classify the portion of the audio signal into one of multiple different classifications (for example, speech, non-speech, music, environment sound, silence, etc.). In one embodiment, these different features include one or more of line spectrum pairs (LSPs), a noise frame ratio, periodicity of particular bands, spectrum flux features, and energy distribution in one or more of the bands. The line spectrum pairs are also optionally used to segment the audio signal, identifying audio classification changes as well as speaker changes when the audio signal is speech.
摘要:
A portion of an audio signal is separated into multiple frames from which one or more different features are extracted. These different features are used, in combination with a set of rules, to classify the portion of the audio signal into one of multiple different classifications (for example, speech, non-speech, music, environment sound, silence, etc.). In one embodiment, these different features include one or more of line spectrum pairs (LSPs), a noise frame ratio, periodicity of particular bands, spectrum flux features, and energy distribution in one or more of the bands. The line spectrum pairs are also optionally used to segment the audio signal, identifying audio classification changes as well as speaker changes when the audio signal is speech.
摘要:
A method of fractal coding of data and apparatus therefor, which method comprises dividing data into domains, determining a set of transformations relating the domains to the data in such a manner as to minimize error between the data and an approximation to the data obtained by application of the transformation, and providing an expression of a series of quantized fractal coefficients characterizing the transformations. A transformation includes at least one part indicating a domain and at least another (functional) part indicating a value for a measure associatable with a specific domain or aspect thereof.
摘要:
A sampling rate conversion apparatus and a method thereof are provided which increase the sampling rate of a discrete audio signal sampled at a predetermined sampling rate by using a fractal interpolation function (FIF). An audio signal portion formed by a predetermined number of sampling data items is divided into a plurality of interpolation intervals. On the audio signal portion, mapping points are determined. The number of the mapping points is in accordance with the degree of increase in the sampling rate. For the respective interpolation intervals, mapping parameters for performing mapping using the FIF on the mapping points are calculated. In all of the interpolation intervals, the mapping using the FIF is performed on the mapping points with the use of the mapping parameters according to the respective interpolation intervals. Thereby, new sampling data items are generated.