Single-microphone speaker separation and voice activity detection in noisy and reverberant environments

Keyphrases

• Reverberant Environment 100%
• Noisy Environment 100%
• Single Microphone 100%
• Speaker Separation 100%
• Voice Activity Detection 100%
• Separation Network 100%
• Speech Signal 66%
• Time-frequency Attention 66%
• Encoder 33%
• Separation Techniques 33%
• Acoustics 33%
• Processing Mode 33%
• Separation Time 33%
• Increasing Complexity 33%
• Human-robot Interaction 33%
• Decoder 33%
• Real Environment 33%
• Humanoid Robot 33%
• Short-time Fourier Transform 33%
• New Architecture 33%
• Block Processing 33%
• Attention Network 33%
• Real-world Experiment 33%
• Overlapped Speech 33%
• Speech Separation 33%
• Support Block 33%
• Inverse Short-time Fourier Transform 33%
• Conv-TasNet 33%

Computer Science

• Time Fourier Transform 100%
• Voice Activity Detection 100%
• Processing Mode 50%
• Simulated Data 50%
• Human Robot Interaction 50%
• Humanoid Robots 50%
• Attention (Machine Learning) 50%
• Temporal Convolutional Network 50%