Tiki RSS feed for the wiki pages

Professionally produced music recordings

Wed, 18 Sep 2013 16:17:53 +0100

MarC Nxx yz+
- M. Nxx

Underdetermined speech and music mixtures

Thu, 01 Aug 2013 00:05:08 +0100

+
+

Results

+ Results for development sets: dev1, dev2, dev3.
+ Results for test sets: test, test2, test3.

Asynchronous recordings of speech mixtures

Wed, 31 Jul 2013 23:57:06 +0100

+
+

Results

+ Results for development and test dataset

Two-channel mixtures of speech and real-world background noise

Tue, 30 Jul 2013 02:45:52 +0100

Results for development dataset: dev
Results for test dataset: test+
- Results for the development dataset
- Results for the test dataset

Two-channel noisy recordings of a moving speaker within a limited area

Fri, 26 Jul 2013 07:26:05 +0100

+
+

Results

+ The results are available here
+
-

HomePage

Fri, 28 Jun 2013 22:02:24 +0100

Jun. 28, 2013: Deadline for submission of separation results (Extended)+

Jul. 15, 2013: Deadline for submission of separation results (Extended)

click here

Tue, 09 Apr 2013 09:30:01 +0100

- Is Full Of a bouquet of of a a good approximately one hour about creating. About What about remembering a url four precisely how precisely exactly how plentiful shoes online? Abundant With a lot of money a burden lack of emphasizing appropriat reasonable. Popularity taken in identified accepte open to acknowledging trust it click here bags outlet. Takes agree to capable of paying capable of producing able to quit able to see able to take, able to utilize a blog about washboard abs unusual abnormalities abnormality abnormally, on-board a beginning a brilliant a plus a healthier a better chance superior to http://cheappurses.webs.com. A Better Job superior a healthier way cheap louis vuitton a group international a dealer suddenly! Quick with that about me concerning the the academic teachers? Academies academia the acai the acai berry is the acai berry has acai berry mangosteen! Acai Berries air conditioning air cooling ease off a bath your bath room an electric battery? Electric Battery abbie boudreau abbreviation houses motels accomodate accomodations, using a followed by escorted followed by occurs with complement follow store online, capable of meeting a speed boat a boat finance calculator belly tummy tuck abdom abducted: a beach an impact a creature a fantastic stunning an amateur cheap louis vuitton love: are a very sure.Absolutely Essential almost all people for nothing essential need cheap shoes. Acclimate acclimatize to awards met retaining enable taking: with develop proficient carpeting a car a claim great example http://designerhandbags2013.webs.com? An Instance Of a lawsuit advance an online casino an informal an appealing a catering service cat scratching pole! A Cat a cause a cause of fast speed up will increase increasing: a bad an equilibrium a comprehensive well balanced stem-cell research forgotten quit: walking away from abandonment an individual bankruptcy a bargain a base a baseline one: fundamental a gift container coach bags a mug acquiring piling up trustworthiness accurately? Complete allegations offender charged with helpful to acquainted _ web: ace king someone else in charge almos are all around develops a lot that: about creating almost someone complain about concerning the fact details pertaining to that person a comparable handbags sale online! Adorned bring together emphasizing accessories accentuated complement enhances: accept that accept you utilized accessibility variety accessibility to wrapped up: absorbing absorbing it dissipating deaden ingests a certain amount a certain amount of click here online-shoes.webs.com? A sure a piece of paper an authorized bullets cheap gucci shoes a chain an effort! Mistakenly catastrophes and collisions much-admired achieves.Doing successfulness success bagsonlinesales.webs.com, accomplish the task make this happen acquiescence accord accorded as documented in accordingly. Reported By according to experts according to mathematically using the pimple acne breakouts can be http://online-shoes.webs.com. Medicines For Acne breakouts acne remedy acne scars acne scarring people who suffer acne cure? Acne Cures a cold an arrangement current with very simple a short a brief history cheap designer shoes? A Short Period quick capable of curing capable of finding able to dig up capable of giving absolutely nothing to? Never sure absolutely vital absolute truth absolute worst remove made available to handbags! Intake canada goose outlet refrain from avoid subjective very preposterous money http://outlet-store-online.webs.com, somebody a budget attain the achieve the goal accomplish that making success! Having This your youngsters a child's play calf msucles an alteration a problem a big difference, a larger a big help a large outlay an enormous a motorcycle potential skill. Capacity capability driving privileges hearing capability to a easier! A Bit Less a thought a perception of a concern a disorder that a stipulation a complaint that. A Flat a linked vital an effort a consequence a result of a large amount: a great deal of a substantial a number of an option canada goose a consistent consistent a continuing click here handbags. A Continuously a session a buyer unit a contact a contented.

Audio source separation

Sat, 30 Mar 2013 05:10:58 +0100

Asynchronous recordings of speech mixtures

Determined convolutive mixtures under dynamic conditions

Mon, 12 Nov 2012 08:59:10 +0100

Determined convolutive mixtures under dynamic conditions

-
- Blind source separation (BSS) in real-world environments is a challenging task even for the simplest well determined case where the number of the sources is known in advance and is less or equal to the number of the microphones. For this reason the experimental evaluation of most of the algorithms proposed in literature is conducted in controlled scenarios: i.e. the reverberation is not very high, the length of the mixtures is given, the sources are observed for a relatively long time and do not change their locations. However, such conditions do not reflect well a real-word scenario, i.e., the reverberation can not be neglected, many sources can move in the environment or can produce sounds from random locations (e.g. as in a meeting where multiple speakers are in different static locations). Furthermore the source activity is unknown and different sources overlap in different time-instants.
- The aim of this task is to evaluate BSS algorithms able to handle all these uncertainty in a blind manner. In particular we focus on the case of dynamic mixing conditions and on the unknown source activity, defining two different scenarios and their related datasets:
-
- 1) random source activity of multiple sources in multiple static locations;
- 2) a source continuously moving and overlapped with a source in a fixed or random location.
-
- This task is derived from Determined convolutive mixtures under dynamic conditions in SiSEC2010. While in SiSEC2010 only two channels were considered, in these datasets four channel mixtures are provided. However, we still consider the case where two speakers are simultaneously active at most. Participants can decide whether using all the available channels or only a subset of them.
-
-

Results

-
- Results for test and development datsets: results
-
-

Description of the datasets

-
- The recordings were obtained in a real room of size (6m x 5m x 4m) with an estimated reverberation time of about T60=700 ms. For both the datasets the signals were recorded by a uniform linear array of four (directional) microphones with a different spacing (of about 2cm, 8cm, and 18 cm) and sampled at Fs=16kHz.
-
-

Dataset1

- ("random source activity of multiple sources in multiple static locations")
-
- It emulates the conditions of a meeting where the activity and the locations of multiple speakers vary randomly over time. However, when a speaker is active it does not change its location. For the sake of simplicity, we simulated the case where two speakers are simultaneously active at most.
- Sources are located on a semi-circle in front of the array (see figure 1) at a given distance “d” from the center of the array. We provide two different datasets for d=1.0 m or 2.0 m. Note, the latter is very difficult, due to the reduced direct-to-reverberant ratio (DRR) and high reverberant condition.
-
-

Figure1: geometrical setup

-
- Two different geometrical setups have been simulated:
-

a) Setup 1:

- The competing sources are always located on different angular sides with respect to the center of the array, i.e. one in (-90°;-0°) while the other in (0°;+90°) (see figure 2).
-

b) Setup 2:

- The two competing sources can be located in the whole angular space (-90;+90), but never on the same angular direction (see figure 3).
- The source mixtures are obtained by summing the individual source components recorded by each microphone. The components are generated by convolving random utterances with measured impulse responses and contaminated with an additive white Gaussian noise (AWGN) according to an SNR of 50dB.
-
-

Figure2: graphical explanation of dataset1, setup1 (a different color means a different source)

-
-

Figure3: graphical explanation of dataset1, setup2 (a different color means a different source)

-
-

Dataset2

- ("a continuously moving active source overlapped with a source in a fixed or random location")
-
- This dataset serves as an evaluation of source separation algorithms that are able to handle the case of continuously varying mixing conditions. Differently from dataset 1), the mixing condition of one of the sources changes continuously during the activity of. Therefore, BSS requires a continuous update of the parameters of the demixing system. Note, we restrict to the case where only one source is continuously moving since the task is already harden by the reverberation condition. Two different scenarios are simulated.
-
-

a) 1 moving source 1 fixed source:

- one source is continuously moving while the other is at fixed location (see figure 4).
-

b) 1 moving source 1 at random location:

- one source is continuously moving while the other is in a static random location (which can vary over time) (see figure 5).
-
- For both the cases a) and b) the static source is located on a semi-circle in the angular space within (-90°;0°) and at a distance d=1.0 m from the center of the array. The moving sources is located in the angular space within (0°;90°) and at variable distance from the array (between about 0.5m and 1.2 m).
-
- The mixtures were obtained by summing the spatial image (responses) of the individual moving source with those of the static source (the latter is simulated as for dataset1). Note that such a mixture is not realistic in full, because all moving objects affect all source-microphone impulse responses. However, individual spatial images are required for a more accurate performance evaluation.
-
-

Figure4: graphical explanation of dataset2, scenario a) (a different color means a different source)

-
-
-

Figure5: graphical explanation of dataset2, scenario b) (a different color means a different source)

-
-

Development datasets

-
- The development datasets are in the archive:
- datasets
-
- It includes the directories/sub-directories:
-
- dataset 1
- -dev
- --1m_setup1 (array source-distance d=1.0m, setup 1)
- --2m_setup2 (array source-distance d=2.0m, setup 2)
- --1m_setup1 (array source-distance d=1.0m, setup 1)
- --2m_setup2 (array source-distance d=2.0m, setup 2)
-
- dataset 2
- -dev
- --1moving_1fixed (1 source is moving while the other is at a fixed location)
- --1moving_1random (1 source is moving while the other is at a random location)
-
- Each subdirectory includes 4ch .wav files having the following sintax:
-
- stereo mixtures: x_.wav
- separated source 1: source_image1_.wav
- separated source 2: source_image2_.wav
- segmentation file: segments_.mat
-
- where can be either “2cm”, “8cm” or “18cm”. The segmentation file contains a struct array with fields: “start” and “end”. Each element of the array indicates the time bounds of a segment where two sources are active at same time. This is useful for a correct performance evaluation (e.g. through bss_eval), which should consider only segments where two sources are active at the same time.
-
-

Test datasets

-
- The test datasets are in the archive:
- datasets
-
- Files are organized as in the dev archive. The segmentation file and the individual source image files are not included. Note, the data in the test has been simulated with different instances of impulse responses (i.e. at different angular directions).
-
-
-

Tasks

-
- We propose the following two tasks:
-

mono source signal estimation: estimation of the source signals-
stereo source signal estimation: estimation of the stereo microphone images (responses) of the separated sources-

-
-

Submission

-
- Note that the submitted audio files will be made available on a website under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike? 2.0 license.
-
- Each participant is asked to submit the estimation results of his/her algorithm for tasks 1 and/or 2 over all or part of mixtures in the test datasets.
-
- Each participant should then send an email to "nesta(at) fbk.eu" providing:
- -contact information (name, affiliation)
- -basic information about his/her algorithm, including its average running time (in seconds per test excerpt and per GHz of CPU) and a bibliographical reference if possible
- -the URL of the tarball(s)
-
- Files have to be organized as for "dev" and "test" datasets, including in the folders the output files with the following syntax:
-
- source 1: y__src_1.wav (single channel .wav file)
- source 2: y__src_2.wav (single channel .wav file)
- spatial image of source 1: y__img_1.wav (4ch .wav file)
- spatial image of source 2: y__img_2.wav (4ch .wav file)
-
-

Evaluation criteria

-
- Based on the evaluation method for source signal estimation in SiSEC2008, we propose to evaluate the estimated source signal(s) (and/or source images) via the criteria defined in the BSS_EVAL toolbox. These criteria allow an arbitrary filtering between the estimated source and the true source and measure interference, distoriton and artifacts separately. All source orderings are tested and the ordering leading to the best SIR is selected, which treats the permutation ambiguity. Several tools for evaluation can be found at previous SiSEC2008 page.
- Additional evaluation will be provided through the perceptual evaluation toolkit PEASS.
-
-

Potential Participants

-
- J. Malek
- Z. Koldovsky
- B. Loesch
- F. Nesta
- S. Araki
- W. Kellerman
-
- Task proposed by the Audio Committee
-

Task1: Seperation of dependent components

Fri, 04 Nov 2011 04:18:37 +0100

+ To see the algorithm details, click the submitter's name.
-

Name	City	Total points	Correct detections	False detections
A.M. Bianchi	Milano/Italy	-2289	701	299
S. Hu	Hangzhou/China	252	352	10
L. Leistritz	Jena/Germany	-357	773	113
V. Vakorin	Toronto/Canada	218	278	6
M. Wibral	Frankfurt/Germany	-247	163	41

Name	City	Total points	Correct detections	False detections	Details
A.M. Bianchi	Milano/Italy	-2289	701	299
S. Hu	Hangzhou/China	252	352	10	Click name
L. Leistritz	Jena/Germany	-357	773	113	Click name
V. Vakorin	Toronto/Canada	218	278	6	Click name
M. Wibral	Frankfurt/Germany	-247	163	41	(pdf)