Sound Demo of LExt on WSJ0-2mix, WHAM! and WHAMR!


This webpage provides a sound demo on the test set of the WSJ0-2mix, WHAM! and WHAMR!. For technical details, please refer to the following paper:

P. Shen, K. Chen, S. He, P. Chen, S. Yuan, H. Kong, X. Zhang, and Z.-Q. Wang, "Listen to Extract: Onset-Prompted Target Speaker Extraction", in submission, 2025.

This demo presents the enhancement results of 20 randomly-selected test signals.
1. 20 randomly-selected test signals in WSJ0-2mix input cases (click to jump to the section)
2. 20 randomly-selected test signals in WHAM! input cases (click to jump to the section)
3. 20 randomly-selected test signals in WHAMR! input cases (click to jump to the section)

wsj0-mix/

Utterance ID=22ho010d_0.64934_420a0104_-0.64934_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=050c0110_0.27669_22go010c_-0.27669_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=440c0213_0.35158_445o030q_-0.35158_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=443c0201_1.8235_445o030t_-1.8235_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=052c010a_1.6182_051a0505_-1.6182_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446c020l_0.2558_441c020x_-0.2558_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=421a010d_2.3751_22go0103_-2.3751_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=442o0305_0.15429_440o030t_-0.15429_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446c020i_1.9128_053o020o_-1.9128_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=22go0103_1.6924_445o030b_-1.6924_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=051c010w_1.3191_444o030n_-1.3191_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444o030p_0.2908_423o0309_-0.2908_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444c0212_1.2944_420c020u_-1.2944_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447o030a_1.0463_053a050j_-1.0463_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=421a010i_1.8649_051o020e_-1.8649_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446o030k_0.24698_051c0112_-0.24698_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447c0208_1.0785_423o030n_-1.0785_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=22hc0101_2.1221_442c0205_-2.1221_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447c020f_2.2307_420a010x_-2.2307_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444c0203_1.2986_053c010n_-1.2986_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target

wham/

Utterance ID=22ho010d_0.64934_420a0104_-0.64934_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=050c0110_0.27669_22go010c_-0.27669_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=440c0213_0.35158_445o030q_-0.35158_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=443c0201_1.8235_445o030t_-1.8235_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=052c010a_1.6182_051a0505_-1.6182_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446c020l_0.2558_441c020x_-0.2558_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=421a010d_2.3751_22go0103_-2.3751_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=442o0305_0.15429_440o030t_-0.15429_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446c020i_1.9128_053o020o_-1.9128_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=22go0103_1.6924_445o030b_-1.6924_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=051c010w_1.3191_444o030n_-1.3191_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444o030p_0.2908_423o0309_-0.2908_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444c0212_1.2944_420c020u_-1.2944_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447o030a_1.0463_053a050j_-1.0463_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=421a010i_1.8649_051o020e_-1.8649_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446o030k_0.24698_051c0112_-0.24698_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447c0208_1.0785_423o030n_-1.0785_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=22hc0101_2.1221_442c0205_-2.1221_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447c020f_2.2307_420a010x_-2.2307_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444c0203_1.2986_053c010n_-1.2986_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target

whamr/

Utterance ID=22ho010d_0.64934_420a0104_-0.64934_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=050c0110_0.27669_22go010c_-0.27669_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=440c0213_0.35158_445o030q_-0.35158_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=443c0201_1.8235_445o030t_-1.8235_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=052c010a_1.6182_051a0505_-1.6182_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446c020l_0.2558_441c020x_-0.2558_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=421a010d_2.3751_22go0103_-2.3751_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=442o0305_0.15429_440o030t_-0.15429_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446c020i_1.9128_053o020o_-1.9128_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=22go0103_1.6924_445o030b_-1.6924_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=051c010w_1.3191_444o030n_-1.3191_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444o030p_0.2908_423o0309_-0.2908_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444c0212_1.2944_420c020u_-1.2944_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447o030a_1.0463_053a050j_-1.0463_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=421a010i_1.8649_051o020e_-1.8649_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=446o030k_0.24698_051c0112_-0.24698_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447c0208_1.0785_423o030n_-1.0785_S1 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=22hc0101_2.1221_442c0205_-2.1221_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=447c020f_2.2307_420a010x_-2.2307_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target
Utterance ID=444c0203_1.2986_053c010n_-1.2986_S0 Target Speaker Log-compreesed Power Spectrogram
Enrollment
Mixture
Estimate
Target