"A Pitch-Synchronous Simultaneous Detection-Estimation
Framework for Speech Enhancement"

Johannes Stahl, Pejman Mowlaee

- Audio samples -

Below, we present some audio samples demonstrating the impact of the proposed pitch-synchronous stochastic-deterministic detection and estimation (PSSDDE) method. The results are shown for the fully blind scenario of male and female utterance corrupted in different noise types and different SNRs.

Proof-of-concept: Female speaker: ''By the look of him he wasn't that far gone'' in white noise, SNR = 0 (dB):

Male speaker: ''Steve wore a bright red cashmere sweater'' in factory noise, SNR = 5 (dB):

Female speaker: ''Why yell or worry over silly items?'' in factory noise, SNR = 5 (dB):

Male speaker: ''Why charge money for such garbage?'' in factory noise, SNR = 15 (dB):

Female speaker: ''Heave on those ropes; the boat's come unstuck.'' in factory noise, SNR = 15 (dB):

Male speaker: ''The nearest synagogue may not be within walking distance.'' in babble noise, SNR = 5 (dB):

Female speaker: ''Basketball can be an entertaining sport.'' in babble noise, SNR = 5 (dB):

Male speaker: ''Sometimes, he coincided with my father's being at home.'' in babble noise, SNR = 15 (dB):

Female speaker: ''Authorities say that oldsters are a prime target.'' in babble noise, SNR = 15 (dB):

Male speaker in a cafe as an example for a real-world scenario. The recording was part of the Chime 4 challenge:
Emmanuel Vincent, Shinji Watanabe, Aditya Arie Nugraha, Jon Barker, and Ricard Marxer "An analysis of environment, microphone and data simulation mismatches in robust speech recognition", Computer Speech and Language, 2016.: