Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

speech enhancement using lms

Status
Not open for further replies.

akshatanayak

Newbie level 6
Joined
Jan 26, 2012
Messages
14
Helped
0
Reputation
0
Reaction score
0
Trophy points
1,281
Activity points
1,400
I implemented an LMS code in matlab for removing the noise present in the speech signal and the noise is getting removed but only before and after the speech segment. ie the noise added over the speech remains the same. I used the following algorithm
1) noise estimation using VAD. I found the speech and noise frames in this step and estimated the noise spectrum from the non-speech frames
2) I passed the noise spectrum along the degraded speech saample to the lms filter.
Both the VAD and lms are working perfectly individually, but merging the two just gives me a correct noise VAD output and my lms output gives me the problem.
Please tell me in what direction do I think? I have attached my code plz help me!!:-?
 

Attachments

  • adaptive.doc
    28.5 KB · Views: 71

How does your filter do if the background amplitude is equal or greater than the voice amplitude?
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top