We provide a sound demo based on the test set of the CHiME-6 corpus. For technical details, please refer to the following paper:
Z.-Q. Wang and S. Cornell, "Cross-Talk Speech Reduction, by Separation, for Separation", in submission, 2026.This demo presents the results of CTRnet with oracle speaker diarization.
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P01 | ![]() |
|
| Mixture (0 of Table II) |
P02 | ![]() |
|
| Mixture (0 of Table II) |
P03 | ![]() |
|
| Mixture (0 of Table II) |
P04 | ![]() |
|
| Supervised (2 of Table II) |
P01 | ![]() |
|
| Supervised (2 of Table II) |
P02 | ![]() |
|
| Supervised (2 of Table II) |
P03 | ![]() |
|
| Supervised (2 of Table II) |
P04 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P01 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P02 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P03 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P04 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P01 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P02 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P03 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P04 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P01 | ![]() |
|
| Mixture (0 of Table II) |
P02 | ![]() |
|
| Mixture (0 of Table II) |
P03 | ![]() |
|
| Mixture (0 of Table II) |
P04 | ![]() |
|
| Supervised (2 of Table II) |
P01 | ![]() |
|
| Supervised (2 of Table II) |
P02 | ![]() |
|
| Supervised (2 of Table II) |
P03 | ![]() |
|
| Supervised (2 of Table II) |
P04 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P01 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P02 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P03 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P04 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P01 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P02 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P03 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P04 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P01 | ![]() |
|
| Mixture (0 of Table II) |
P02 | ![]() |
|
| Mixture (0 of Table II) |
P03 | ![]() |
|
| Mixture (0 of Table II) |
P04 | ![]() |
|
| Supervised (2 of Table II) |
P01 | ![]() |
|
| Supervised (2 of Table II) |
P02 | ![]() |
|
| Supervised (2 of Table II) |
P03 | ![]() |
|
| Supervised (2 of Table II) |
P04 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P01 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P02 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P03 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P04 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P01 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P02 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P03 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P04 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P01 | ![]() |
|
| Mixture (0 of Table II) |
P02 | ![]() |
|
| Mixture (0 of Table II) |
P03 | ![]() |
|
| Mixture (0 of Table II) |
P04 | ![]() |
|
| Supervised (2 of Table II) |
P01 | ![]() |
|
| Supervised (2 of Table II) |
P02 | ![]() |
|
| Supervised (2 of Table II) |
P03 | ![]() |
|
| Supervised (2 of Table II) |
P04 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P01 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P02 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P03 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P04 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P01 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P02 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P03 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P04 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P01 | ![]() |
|
| Mixture (0 of Table II) |
P02 | ![]() |
|
| Mixture (0 of Table II) |
P03 | ![]() |
|
| Mixture (0 of Table II) |
P04 | ![]() |
|
| Supervised (2 of Table II) |
P01 | ![]() |
|
| Supervised (2 of Table II) |
P02 | ![]() |
|
| Supervised (2 of Table II) |
P03 | ![]() |
|
| Supervised (2 of Table II) |
P04 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P01 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P02 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P03 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P04 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P01 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P02 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P03 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P04 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P01 | ![]() |
|
| Mixture (0 of Table II) |
P02 | ![]() |
|
| Mixture (0 of Table II) |
P03 | ![]() |
|
| Mixture (0 of Table II) |
P04 | ![]() |
|
| Supervised (2 of Table II) |
P01 | ![]() |
|
| Supervised (2 of Table II) |
P02 | ![]() |
|
| Supervised (2 of Table II) |
P03 | ![]() |
|
| Supervised (2 of Table II) |
P04 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P01 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P02 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P03 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P04 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P01 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P02 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P03 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P04 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P01 | ![]() |
|
| Mixture (0 of Table II) |
P02 | ![]() |
|
| Mixture (0 of Table II) |
P03 | ![]() |
|
| Mixture (0 of Table II) |
P04 | ![]() |
|
| Supervised (2 of Table II) |
P01 | ![]() |
|
| Supervised (2 of Table II) |
P02 | ![]() |
|
| Supervised (2 of Table II) |
P03 | ![]() |
|
| Supervised (2 of Table II) |
P04 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P01 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P02 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P03 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P04 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P01 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P02 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P03 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P04 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P45 | ![]() |
|
| Mixture (0 of Table II) |
P46 | ![]() |
|
| Mixture (0 of Table II) |
P47 | ![]() |
|
| Mixture (0 of Table II) |
P48 | ![]() |
|
| Supervised (2 of Table II) |
P45 | ![]() |
|
| Supervised (2 of Table II) |
P46 | ![]() |
|
| Supervised (2 of Table II) |
P47 | ![]() |
|
| Supervised (2 of Table II) |
P48 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P45 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P46 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P47 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P48 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P45 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P46 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P47 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P48 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P45 | ![]() |
|
| Mixture (0 of Table II) |
P46 | ![]() |
|
| Mixture (0 of Table II) |
P47 | ![]() |
|
| Mixture (0 of Table II) |
P48 | ![]() |
|
| Supervised (2 of Table II) |
P45 | ![]() |
|
| Supervised (2 of Table II) |
P46 | ![]() |
|
| Supervised (2 of Table II) |
P47 | ![]() |
|
| Supervised (2 of Table II) |
P48 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P45 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P46 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P47 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P48 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P45 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P46 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P47 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P48 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P45 | ![]() |
|
| Mixture (0 of Table II) |
P46 | ![]() |
|
| Mixture (0 of Table II) |
P47 | ![]() |
|
| Mixture (0 of Table II) |
P48 | ![]() |
|
| Supervised (2 of Table II) |
P45 | ![]() |
|
| Supervised (2 of Table II) |
P46 | ![]() |
|
| Supervised (2 of Table II) |
P47 | ![]() |
|
| Supervised (2 of Table II) |
P48 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P45 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P46 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P47 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P48 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P45 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P46 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P47 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P48 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P45 | ![]() |
|
| Mixture (0 of Table II) |
P46 | ![]() |
|
| Mixture (0 of Table II) |
P47 | ![]() |
|
| Mixture (0 of Table II) |
P48 | ![]() |
|
| Supervised (2 of Table II) |
P45 | ![]() |
|
| Supervised (2 of Table II) |
P46 | ![]() |
|
| Supervised (2 of Table II) |
P47 | ![]() |
|
| Supervised (2 of Table II) |
P48 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P45 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P46 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P47 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P48 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P45 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P46 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P47 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P48 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P45 | ![]() |
|
| Mixture (0 of Table II) |
P46 | ![]() |
|
| Mixture (0 of Table II) |
P47 | ![]() |
|
| Mixture (0 of Table II) |
P48 | ![]() |
|
| Supervised (2 of Table II) |
P45 | ![]() |
|
| Supervised (2 of Table II) |
P46 | ![]() |
|
| Supervised (2 of Table II) |
P47 | ![]() |
|
| Supervised (2 of Table II) |
P48 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P45 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P46 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P47 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P48 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P45 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P46 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P47 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P48 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P45 | ![]() |
|
| Mixture (0 of Table II) |
P46 | ![]() |
|
| Mixture (0 of Table II) |
P47 | ![]() |
|
| Mixture (0 of Table II) |
P48 | ![]() |
|
| Supervised (2 of Table II) |
P45 | ![]() |
|
| Supervised (2 of Table II) |
P46 | ![]() |
|
| Supervised (2 of Table II) |
P47 | ![]() |
|
| Supervised (2 of Table II) |
P48 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P45 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P46 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P47 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P48 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P45 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P46 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P47 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P48 | ![]() |
|
Signal segment: |
|||
| Systems | Speaker | Signal | Log-compreesed Power Spectrogram |
| Mixture (0 of Table II) |
P45 | ![]() |
|
| Mixture (0 of Table II) |
P46 | ![]() |
|
| Mixture (0 of Table II) |
P47 | ![]() |
|
| Mixture (0 of Table II) |
P48 | ![]() |
|
| Supervised (2 of Table II) |
P45 | ![]() |
|
| Supervised (2 of Table II) |
P46 | ![]() |
|
| Supervised (2 of Table II) |
P47 | ![]() |
|
| Supervised (2 of Table II) |
P48 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P45 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P46 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P47 | ![]() |
|
| GSS (8-channel) (1b of Table II) |
P48 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P45 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P46 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P47 | ![]() |
|
| Semi-sup. CTRnet (10b of Table II) |
P48 | ![]() |