Databases
StackOverflow2013
Postsdbo
PO
 

Note that there are some explanatory texts on larger screens.

plurals
  1. PO
    primarykey
    data
    text
    <p>Had to make this an answer as it's simply too long for a comment.</p> <p>I'm basically working in this field right now so I feel I have some knowledge. Obviously from my standpoint I'd recommend working with audio rather than images. I also recommend using MFCCs as your feature extraction (which you can think of as coefficients which summarise/characterise specific sub-bands of audio frequency [because they are]).</p> <p>GMMs are the go.</p> <p>To perform this task you <strong>must</strong> have some (preferably a lot) of <strong>labelled/known</strong> data, otherwise there is no basis for the machine learning to take place.</p> <p><strong>A technicality which you may find useful:</strong></p> <blockquote> <p>'Then, during testing, you submit a query MFCC vector to the GMM, and it will tell you which species it thinks it is.'</p> </blockquote> <p>More accurately, you submit a query to each GMM (which if you're using them correctly, each gives you a likelihood score [probability] of that particular feature vector being emitted by that probability distribution). Then you compare all the likelihood scores you receive from all the GMMs and classify based on the highest you receive.</p> <p><strong>UBMs</strong></p> <p>Rather than "filtering out" noise, you can simply model all background noise/channel distortion with a UBM (Universal Background Model). This model consists of a GMM trained using all the training data available to you (that is, all the training data you used for each class). You can use this to get a 'likelihood ratio' (<em>Pr</em>[x would be emitted by specific model] / <em>Pr</em>[x would be emitted by background model (UBM)]) to help remove any biasing that can be explained by the background model itself.</p>
    singulars
    1. This table or related slice is empty.
    1. POBirdsong audio analysis - finding how well two clips match
      singulars
      1. PTQuestion
    1. PTAnswer
    1. USWilliam
    1. USWilliam
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. POBirdsong audio analysis - finding how well two clips match
      singulars
      1. PTQuestion
    1. This table or related slice is empty.
    1. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    2. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    3. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    1. COJust need to comment: HMMs are **NOT** well-described as "multiple state GMMs". HMMs reflect the short-term temporal relationships within data, whereas GMMs have no concept of time built in. HMMs don't have to use Gaussian mixtures, but GMMs do. HMMs have a separation between hidden state and observation, GMMs don't. In case it's of use, here's a free Python MFCC+GMM implementation which reflects the basic model discussed here: https://github.com/danstowell/smacpy
      singulars
      1. PO
      1. USDan Stowell
    2. CO@DanS I agree with you completely. The concept of GMM and HMM given in this question are incorrect.
      singulars
      1. PO
      1. USlightalchemist
 

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.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload