AUDIBLE Graphs - Revision history

Dominic at 21:08, 10 November 2008

2008-11-10T21:08:02Z

Dominic at 16:31, 10 November 2008

2008-11-10T16:31:49Z

← Older revision		Revision as of 16:31, 10 November 2008
Line 1:		Line 1:
			[[AUDIBLE\|Return to AUDIBLE]]

	= Microphone Array Source Separation =		= Microphone Array Source Separation =
	The following demonstrates the use of a microphone array for separating three simultaneous speech sources in presence of both reverberation and background noise.		The following demonstrates the use of a microphone array for separating three simultaneous speech sources in presence of both reverberation and background noise.

Dominic at 16:26, 10 November 2008

2008-11-10T16:26:01Z

← Older revision		Revision as of 16:26, 10 November 2008
Line 43:		Line 43:
	== Reference (original) sources ==		== Reference (original) sources ==
	These signals are provided here for reference only and correspond to the real (unknown to the algorithm) sources.		These signals are provided here for reference only and correspond to the real (unknown to the algorithm) sources.
			<center>
	* Source 1 (wav)		{\|
	* Source 2 (wav)		\|[[Image:AUDIBLE_Reference1.jpg]]
	* Source 3 (wav)		\|[[Image:AUDIBLE_Reference2.jpg]]
			\|[[Image:AUDIBLE_Reference3.jpg]]
			\|-
			\|[[Media:AUDIBLE_Reference1.wav\|Source 1 (wav)]]
			\|[[Media:AUDIBLE_Reference2.wav\|Source 2 (wav)]]
			\|[[Media:AUDIBLE_Reference3.wav\|Source 3 (wav)]]
			\|}
			</center>

Dominic: /* Separated sources after Geometric Source Separation (GSS) and post-filter */

2008-11-10T16:20:31Z

Separated sources after Geometric Source Separation (GSS) and post-filter

← Older revision		Revision as of 16:20, 10 November 2008
Line 29:		Line 29:
	== Separated sources after Geometric Source Separation (GSS) and post-filter ==		== Separated sources after Geometric Source Separation (GSS) and post-filter ==
	The signals presented here is the result obtained after applying our post-filter to the output of the GSS algorithm. Our post-filter is able to remove most of the remaining background noise and interferences at the expense of minor distortion to the source of interest.		The signals presented here is the result obtained after applying our post-filter to the output of the GSS algorithm. Our post-filter is able to remove most of the remaining background noise and interferences at the expense of minor distortion to the source of interest.
			<center>
	{\|		{\|
	\|[[Image:AUDIBLE_SeparatedFiltered1.jpg]]		\|[[Image:AUDIBLE_SeparatedFiltered1.jpg]]
Line 39:		Line 39:
	\|[[Media:AUDIBLE_SeparatedFiltered3.wav\|Source 3 (wav)]]		\|[[Media:AUDIBLE_SeparatedFiltered3.wav\|Source 3 (wav)]]
	\|}		\|}
			</center>

	== Reference (original) sources ==		== Reference (original) sources ==

Dominic at 16:20, 10 November 2008

2008-11-10T16:20:12Z

← Older revision		Revision as of 16:20, 10 November 2008
Line 30:		Line 30:
	The signals presented here is the result obtained after applying our post-filter to the output of the GSS algorithm. Our post-filter is able to remove most of the remaining background noise and interferences at the expense of minor distortion to the source of interest.		The signals presented here is the result obtained after applying our post-filter to the output of the GSS algorithm. Our post-filter is able to remove most of the remaining background noise and interferences at the expense of minor distortion to the source of interest.

	* Source 1 (wav)		{\|
	* Source 2 (wav)		\|[[Image:AUDIBLE_SeparatedFiltered1.jpg]]
	* Source 3 (wav)		\|[[Image:AUDIBLE_SeparatedFiltered2.jpg]]
			\|[[Image:AUDIBLE_SeparatedFiltered3.jpg]]
			\|-
			\|[[Media:AUDIBLE_SeparatedFiltered1.wav\|Source 1 (wav)]]
			\|[[Media:AUDIBLE_SeparatedFiltered2.wav\|Source 2 (wav)]]
			\|[[Media:AUDIBLE_SeparatedFiltered3.wav\|Source 3 (wav)]]
			\|}

	== Reference (original) sources ==		== Reference (original) sources ==

Dominic: /* Signal at microphone output */

2008-11-10T16:18:32Z

Signal at microphone output

← Older revision		Revision as of 16:18, 10 November 2008
Line 8:		Line 8:
	[[Image:AUDIBLE_MicrophoneOutput.jpg]]		[[Image:AUDIBLE_MicrophoneOutput.jpg]]

	[[Media:AUDIBLE_MicrophoneOutput.wav\|Signal at microphone output]]		[[Media:AUDIBLE_MicrophoneOutput.wav\|Signal at microphone output (wav)]]
	</center>		</center>



	== Separated sources after Geometric Source Separation (GSS) only ==		== Separated sources after Geometric Source Separation (GSS) only ==

Dominic: /* Signal at microphone output */

2008-11-10T16:15:46Z

Signal at microphone output

← Older revision		Revision as of 16:15, 10 November 2008
Line 3:		Line 3:

	== Signal at microphone output ==		== Signal at microphone output ==
			The signals below is taken directly from one of the microphones in the array. It shows all three sources, mixed with background noise.

	<center>		<center>
Line 9:		Line 10:
	[[Media:AUDIBLE_MicrophoneOutput.wav\|Signal at microphone output]]		[[Media:AUDIBLE_MicrophoneOutput.wav\|Signal at microphone output]]
	</center>		</center>
	~~The signals below is taken directly from one of the microphones in the array. It shows all three sources, mixed with background noise.~~


	~~Microphone (wav)~~
	Separated sources after Geometric Source Separation (GSS) only		== Separated sources after Geometric Source Separation (GSS) only ==
	The signals shown here demonstrates the capabilities of the Geometric Source Separation (GSS) algorithm we use. While interference can still be heard, its level is lower than for a single microphone.		The signals shown here demonstrates the capabilities of the Geometric Source Separation (GSS) algorithm we use. While interference can still be heard, its level is lower than for a single microphone.

	Source 1 (wav)		<center>
			{\|
	Source 2 (wav)		\|[[Image:AUDIBLE_Separated1.jpg]]
			\|[[Image:AUDIBLE_Separated2.jpg]]
	Source 3 (wav)		\|[[Image:AUDIBLE_Separated3.jpg]]
	Separated sources after Geometric Source Separation (GSS) and post-filter		\|-
			\|[[Media:AUDIBLE_Separated1.wav\|Source 1 (wav)]]
			\|[[Media:AUDIBLE_Separated2.wav\|Source 2 (wav)]]
			\|[[Media:AUDIBLE_Separated3.wav\|Source 3 (wav)]]
			\|}

			</center>

			== Separated sources after Geometric Source Separation (GSS) and post-filter ==
	The signals presented here is the result obtained after applying our post-filter to the output of the GSS algorithm. Our post-filter is able to remove most of the remaining background noise and interferences at the expense of minor distortion to the source of interest.		The signals presented here is the result obtained after applying our post-filter to the output of the GSS algorithm. Our post-filter is able to remove most of the remaining background noise and interferences at the expense of minor distortion to the source of interest.

	Source 1 (wav)		* Source 1 (wav)
			* Source 2 (wav)
	Source 2 (wav)		* Source 3 (wav)

	Source 3 (wav)		== Reference (original) sources ==
	Reference (original) sources
	These signals are provided here for reference only and correspond to the real (unknown to the algorithm) sources.		These signals are provided here for reference only and correspond to the real (unknown to the algorithm) sources.

	Source 1 (wav)		* Source 1 (wav)
			* Source 2 (wav)
	Source 2 (wav)		* Source 3 (wav)

	Source 3 (wav)

Dominic: /* Signal at microphone output */

2008-11-10T16:10:19Z

Signal at microphone output

← Older revision		Revision as of 16:10, 10 November 2008
Line 7:		Line 7:
	[[Image:AUDIBLE_MicrophoneOutput.jpg]]		[[Image:AUDIBLE_MicrophoneOutput.jpg]]

	[[Media:AUDIBLE_MicrophoneOutput.wav]]		[[Media:AUDIBLE_MicrophoneOutput.wav\|Signal at microphone output]]
	</center>		</center>
	The signals below is taken directly from one of the microphones in the array. It shows all three sources, mixed with background noise.		The signals below is taken directly from one of the microphones in the array. It shows all three sources, mixed with background noise.

Dominic: New page: = Microphone Array Source Separation = The following demonstrates the use of a microphone array for separating three simultaneous speech sources in presence of both reverberation and backg...

2008-11-10T16:08:08Z

New page: = Microphone Array Source Separation = The following demonstrates the use of a microphone array for separating three simultaneous speech sources in presence of both reverberation and backg...

New page

= Microphone Array Source Separation =
The following demonstrates the use of a microphone array for separating three simultaneous speech sources in presence of both reverberation and background noise.

== Signal at microphone output ==

<center>
[[Image:AUDIBLE_MicrophoneOutput.jpg]]

[[Media:AUDIBLE_MicrophoneOutput.wav]]
</center>
The signals below is taken directly from one of the microphones in the array. It shows all three sources, mixed with background noise.

Microphone (wav)
Separated sources after Geometric Source Separation (GSS) only
The signals shown here demonstrates the capabilities of the Geometric Source Separation (GSS) algorithm we use. While interference can still be heard, its level is lower than for a single microphone.

Source 1 (wav)

Source 2 (wav)

Source 3 (wav)
Separated sources after Geometric Source Separation (GSS) and post-filter
The signals presented here is the result obtained after applying our post-filter to the output of the GSS algorithm. Our post-filter is able to remove most of the remaining background noise and interferences at the expense of minor distortion to the source of interest.

Source 1 (wav)

Source 2 (wav)

Source 3 (wav)
Reference (original) sources
These signals are provided here for reference only and correspond to the real (unknown to the algorithm) sources.

Source 1 (wav)

Source 2 (wav)

Source 3 (wav)

← Older revision		Revision as of 21:08, 10 November 2008
Line 21:		Line 21:
	\|[[Image:AUDIBLE_Separated2.jpg]]		\|[[Image:AUDIBLE_Separated2.jpg]]
	\|[[Image:AUDIBLE_Separated3.jpg]]		\|[[Image:AUDIBLE_Separated3.jpg]]
	\|-		\|- align="center"
	\|[[Media:AUDIBLE_Separated1.wav\|Source 1 (wav)]]		\|[[Media:AUDIBLE_Separated1.wav\|Source 1 (wav)]]
	\|[[Media:AUDIBLE_Separated2.wav\|Source 2 (wav)]]		\|[[Media:AUDIBLE_Separated2.wav\|Source 2 (wav)]]
Line 36:		Line 36:
	\|[[Image:AUDIBLE_SeparatedFiltered2.jpg]]		\|[[Image:AUDIBLE_SeparatedFiltered2.jpg]]
	\|[[Image:AUDIBLE_SeparatedFiltered3.jpg]]		\|[[Image:AUDIBLE_SeparatedFiltered3.jpg]]
	\|-		\|- align="center"
	\|[[Media:AUDIBLE_SeparatedFiltered1.wav\|Source 1 (wav)]]		\|[[Media:AUDIBLE_SeparatedFiltered1.wav\|Source 1 (wav)]]
	\|[[Media:AUDIBLE_SeparatedFiltered2.wav\|Source 2 (wav)]]		\|[[Media:AUDIBLE_SeparatedFiltered2.wav\|Source 2 (wav)]]
Line 50:		Line 50:
	\|[[Image:AUDIBLE_Reference2.jpg]]		\|[[Image:AUDIBLE_Reference2.jpg]]
	\|[[Image:AUDIBLE_Reference3.jpg]]		\|[[Image:AUDIBLE_Reference3.jpg]]
	\|-		\|- align="center"
	\|[[Media:AUDIBLE_Reference1.wav\|Source 1 (wav)]]		\|[[Media:AUDIBLE_Reference1.wav\|Source 1 (wav)]]
	\|[[Media:AUDIBLE_Reference2.wav\|Source 2 (wav)]]		\|[[Media:AUDIBLE_Reference2.wav\|Source 2 (wav)]]