Abstract
A deep neural networks (DNN) based close talk speech segregation algorithm is introduced. One nearby microphone is used to collect the target speech as close talk indicated, and another microphone is used to get the noise in environments. The time and energy difference between the two microphones signal is used as the segregation cue. A DNN estimator on each frequency channel is used to calculate the parameter masks. The parameter masks represent the target speech energy in each time frequency (T-F) units. Experiment results show the good performance of the proposed system. The signal to noise ratio (SNR) improvement is 8.1 dB on 0 dB noisy environment.
Highlights
The noise is a big problem in speech communications and sound collections
The auditory signal is first decomposed to various frequency channels and generated as the time frequency (T-F) units
The deep neural networks (DNN) [4] is used as a signal to noise ratio (SNR) estimator to calculate the energy in each T-F unit with a parameter mask
Summary
The noise is a big problem in speech communications and sound collections. It distorts the clean speech and reduces its intelligence, and make the speech hard to understanding. We usually use close talk microphone to collect the speech with small distance between the microphone and mouth Such as mobile phone, headset microphone and so on, they can get better result than faraway microphone. With the development of auditory scene analysis (ASA), scientists conclude and simulate the ability of hearing system with the computational auditory scene analysis (CASA) algorithm [1]. In this frame work, the auditory signal is first decomposed to various frequency channels and generated as the time frequency (T-F) units. The DNN [4] is used as a signal to noise ratio (SNR) estimator to calculate the energy in each T-F unit with a parameter mask.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
