Displaying 4 results from an estimated 4 matches for "noise_suppress".
2014 Jan 08
1
Some Speex AGC Questions
...39;s not clear
if preprocess is actually doing anything.
If I turn AGC on, the sound level becomes almost inaudible.
When I print the control parameters (the defaults), I get:
DENOISE = 1
AGC = 0
AGC_LEVEL = 1174011904
AGC_INCREMENT = 12
AGC_DECREMENT = -40
AGC_MAX_GAIN = 30
VAD = 0
DEREVERB = 0
NOISE_SUPPRESS = -15
QUESTION number 1: Is there a guide to "tuning" the AGC? Is there a
document that tells what they really mean and how to adjust them?
QUESTION number 2: I see that VAD, DEREVERB, DENOISE, ... have values of
0 or 1. The documentation says that 1 means ON and 2 means OFF. Can
so...
2014 Jan 04
0
Some Speex AGC Questions
...39;s not clear
if preprocess is actually doing anything.
If I turn AGC on, the sound level becomes almost inaudible.
When I print the control parameters (the defaults), I get:
DENOISE = 1
AGC = 0
AGC_LEVEL = 1174011904
AGC_INCREMENT = 12
AGC_DECREMENT = -40
AGC_MAX_GAIN = 30
VAD = 0
DEREVERB = 0
NOISE_SUPPRESS = -15
QUESTION number 1: Is there a guide to "tuning" the AGC? Is there a
document that tells what they really mean and how to adjust them?
QUESTION number 2: I see that VAD, DEREVERB, DENOISE, ... have values of
0 or 1. The documentation says that 1 means ON and 2 means OFF. Can
so...
2010 Jul 15
3
Speex Echo Cancellation
> Message: 1
> Date: Thu, 15 Jul 2010 00:19:43 -0600
> From: devi at purpletalk.com
> Subject: [Speex-dev] Speex Echo Cancellation
> To: speex-dev at xiph.org
> Message-ID: <20100715001943.pr04hvtxsc8k04so at mail.purpletalk.com>
> Content-Type: text/plain; charset=ISO-8859-1; DelSp="Yes";
> format="flowed"
>
> Hi
>
> I am using speex
2009 Jun 24
2
Speech switching in speakerphone?
>> I think the residual echo estimation is fairly reliable but I do not know
>> how to use this to improve Pframe and in that way solve our main problem
>> with the gain during near end talk.
>
> How can you tell that the residual echo estimation is reliable? in any
> case, I suspect that the whole Pframe idea might have to be revised
> (i.e. computing it completely