Speech processing
AssigneeTencent Technology (Shenzhen) Company Limited
InventorsJun Huang, Yannan Wang
Life of this patent
Estimating the term…
Abstract
In an audio processing method, an initial audio feature of initial audio data is obtained. The initial audio feature is input to an audio enhancement model. The audio enhancement model is iteratively trained based on a deep clustering loss function and a mask inference loss function. Target audio data with reduced noise and reverberation is calculated according to a target audio feature. The target audio feature is generated by the audio enhancement model based on the initial audio feature. The target audio data is output.
Claims20
An audio processing method comprising:
- obtaining an initial audio feature of initial audio data;
- inputting the initial audio feature to an audio enhancement model, the audio enhancement model being iteratively trained based on a training sample set, a deep clustering loss function of a clustering training annotation and a deep clustering annotation of the training sample set, and a mask inference loss function of (i) a clean audio training feature and a clean audio label of the training sample set and (ii) a noise audio training feature and a noise audio label of the training sample set;
- calculating, by processing circuitry, target audio data with reduced noise and reverberation according to a target audio feature, the target audio feature being generated by the audio enhancement model based on the initial audio feature;
- and
- outputting the target audio data.
An information processing apparatus, comprising:
- processing circuitry configured to:
- obtain an initial audio feature of initial audio data;
- input the initial audio feature to an audio enhancement model, the audio enhancement model being iteratively trained based on a training sample set, a deep clustering loss function of a clustering training annotation and a deep clustering annotation of the training sample set, and a mask inference loss function of (i) a clean audio training feature and a clean audio label of the training sample set and (ii) a noise audio training feature and a noise audio label of the training sample set;
- calculate target audio data with reduced noise and reverberation according to a target audio feature, the target audio feature being generated by the audio enhancement model based on the initial audio feature;
- and
- output the target audio data.
A non-transitory computer-readable storage medium, storing instructions which when executed by a processor cause the processor to perform:
- obtaining an initial audio feature of initial audio data;
- inputting the initial audio feature to an audio enhancement model, the audio enhancement model being iteratively trained based on a training sample set, a deep clustering loss function of a clustering training annotation and a deep clustering annotation of the training sample set, and a mask inference loss function of (i) a clean audio training feature and a clean audio label of the training sample set and (ii) a noise audio training feature and a noise audio label of the training sample set;
- calculating target audio data with reduced noise and reverberation according to a target audio feature generated by the audio enhancement model based on the initial audio feature;
- and
- outputting the target audio data.
Dependencies are inferred from the claim text.