Databases
StackOverflow2013
Postsdbo
POSegmentation of a voice
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POSegmentation of a voice
    primarykey
    data
    text
    <p>I'm helping a farm to cluster the cocks in groups according to their crowing such that cocks with similar crowing will live together. The farmer said he wants to know whether chickens will learn any behaviors from others, if so, whenever he gets a chick he will put it into a good chickens group and hopes it will bring some good influence to the new chick. My work is to record the crowing similarity of each group, and after few weeks, compare the results and see any increasing similarity in the groups.</p> <p>My idea is to write a program that gives a similarity score for two input wav files, therefore each cock can find its most similar roommate and get paired into groups, and then group the similar groups, finally in a number of groups.</p> <p>I've got some crowings by 3 cocks, and analysed with spectrograms (each cock crowed twice):</p> <p>cock A:</p> <p><img src="https://i.stack.imgur.com/pE042.jpg" alt="first crowing from cock A"> <img src="https://i.stack.imgur.com/GchPo.jpg" alt="second crowing from cock A"></p> <p>cock B:</p> <p><img src="https://i.stack.imgur.com/N15eQ.jpg" alt="first crowing from cock B"> <img src="https://i.stack.imgur.com/JsUoA.jpg" alt="second crowing from cock B"></p> <p>cock C:</p> <p><img src="https://i.stack.imgur.com/okhGB.jpg" alt="first crowing from cock C"> <img src="https://i.stack.imgur.com/0Nytj.jpg" alt="second crowing from cock C"></p> <p>Before calculating the similarity, I would like to split the crowing into segments, such that each segment retains a degree of frequency (which will be used to calculate the similarity later). My current solution is:</p> <p><strong>Step 1:</strong> when the line of intensity is discontinuous, the sound will be splitted by the gaps;<br> <strong>Step 2:</strong> when there is a critical changing in frequency, that time will be considered as a boundary of a segment</p> <p>I'm thinking of the steps above are sufficient or not. I'm hoping that anyone else has a better suggestion and how can I improve the segmentation. Is there any methods or algorithms are suitable for my situation? Thanks!</p>
    singulars
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PTQuestion
    1. USShai
    1. USc'quet
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PO
      singulars
      1. PTAnswer
    2. PO
      singulars
      1. PTAnswer
    1. VO
      singulars
      1. POSegmentation of a voice
      1. USxmoex
      1. VTFavorite
    2. VO
      singulars
      1. POSegmentation of a voice
      1. USc'quet
      1. VTFavorite
    3. VO
      singulars
      1. POSegmentation of a voice
      1. USxiaoxian
      1. VTFavorite
    1. COMaybe you should take a look at [DTW](http://en.wikipedia.org/wiki/Dynamic_time_warping) algorithm.
      singulars
      1. POSegmentation of a voice
      1. USakademi4eg
 

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