StackOverflow2013

Note that there are some explanatory texts on larger screens.

plurals

PO
primarykey
Id
17007591
data
AcceptedAnswerId
0
AnswerCount
0
ClosedDate
CommentCount
1
CommunityOwnedDate
CreationDate
2013-06-09T07:55:41.913
FavoriteCount
0
LastActivityDate
2013-06-09T07:55:41.913
LastEditDate
LastEditorUserId
0
OwnerUserId
478237
ParentId
15510109
PostTypeId
2
Score
2
ViewCount
0
LastEditorDisplayName
text
Body
You are asking for voice identification or voice verification, which is one of the many uses of voice analysis. Beware, voice identification is far from perfect. You would first need training data and algorithms, from which you would deduce statistical models for your speaker. Later, in the recognition/verification phase, you would try to fit input data against your statistical models and determine the threshold, which decides if the speaker is known or not. Some keywords if you would go about implementing this by yourself or just looking for more technical info are Mel frequency cepstral coefficients, Gaussian mixture models and Hidden markov models. An interesting tool might be <a href="http://www.fon.hum.uva.nl/praat/" rel="nofollow">Praat</a>. It's not available as library directly, but people at ICSI have written a wrapper called <a href="http://www.icsi.berkeley.edu/icsi/groups/speech/software" rel="nofollow">praatlib</a>. It extracts speech features such as formant frequency, pitch, and some more. ICSI used it for distinguishing between speakers within a recording (this is called diarization). There are quite some free tools available, but all require an in-depth understanding of statistics, speech analysis and extensive amount of time in order to understand typically underdocumented academic code. Some interesting projects you should take a look at are <a href="http://cmusphinx.sourceforge.net/" rel="nofollow">Sphinx</a> (Java) and <a href="http://shout-toolkit.sourceforge.net/" rel="nofollow">SHoUT</a> (C++). Sphinx has good documentation, and SHoUT has a dissertation you can read if you find yourself questioning theoretical details.
Tags
Title
singulars
PostAcceptedAnswerId
1. This table or related slice is empty.
PostParentId
1. POhow to detect who is speaking
 singulars
 PostTypePostTypeId
 PTQuestion
PostTypePostTypeId
1. PTAnswer
UserLastEditorUserId
1. This table or related slice is empty.
UserOwnerUserId
1. UShruske
plurals
PostLinksPostIdRelatedPostId
1. This table or related slice is empty.
PostLinksRelatedPostIdPostId
1. This table or related slice is empty.
PostsAcceptedAnswerId
1. This table or related slice is empty.
PostsParentIdCreationDate
1. This table or related slice is empty.
VotesPostIdCreationDate
1. VO
 singulars
 PostPostId
 PO
 UserUserId
 This table or related slice is empty.
 VoteTypeVoteTypeId
 VTUpMod
CommentsPostId
1. COThank you for your input.
 singulars
 PostPostId
 PO
 UserUserId
 USskmasq

Querying!

Guidance

A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.