Separating generalized stereophonic background from panning sources using minimal training

• Main Author: MAST, ARVIND, S
• Format: Patent
• Language: Chinese; English
• Published: 03.02.2023
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

In an embodiment, a spatial level filter (SLF) is created by obtaining a first set of samples from a plurality of target source level distributions and a spatial distribution in a sub-band in the frequency domain; obtaining a second set of samples from a plurality of background level distributions and spatial distributions in sub-bands in the frequency domain; adding the first sample set and the second sample set to create a combined sample set; for each sub-band, detecting a level parameter and a space parameter of each sample in the combined sample set; weighting detected level parameters and space parameters through corresponding level distribution and space distribution of a target source and a background in the sub-band; storing a weighted level parameter, a spatial parameter and a signal-to-noise ratio (SNR) of each sample in the combined sample set in the sub-band in a table; and re-indexing the table by sub-bands and weighted level and spatial parameters. 在实施例中，通过以下方式创建空间电平滤波器(SLF)：从频域中的子频带中的多个目标源电平分布