A joint learning algorithm for complex-valued t-f masks in deep learning-based single-channel speech enhancement systems

Computer Science

• Algorithms 33%
• Evaluation Result 33%
• Frequency Domain 33%
• Learning Algorithm 100%
• Learning Framework 33%
• Learning Method 66%
• Learning Network 33%
• Learning Process 66%
• Objective Function 33%
• Objective Measure 33%
• Performance Improvement 33%
• Phase Component 33%
• Single Channel 100%
• Subjective Preference 33%

Physics

• Complex Numbers 33%
• Distortion 33%
• Dynamic Range 66%
• Sound Quality 33%
• Spectrogram 33%