Speeker Identification (Machine Learning)

by

There are a lot of resources available, books, journals, sources, programs. But let me suggest very simple algorithm.
1. Train/Save HMM acoustic model for each speaker. If u have 10 speakers, than u have ten models.

  1. Now ask a current speaker to say magic words like ‘Ok google’. Now recognize it against every models saved. So u have scores for every model. of course the right speaker is the model with highest score.

Which with HTK only bash/shell programming is required. No c/python or matlab involved

More Related Contents:

  1. Machine understand natural language – nlp [closed]
  2. Keras Text Preprocessing – Saving Tokenizer object to file for scoring
  3. How does Apple find dates, times and addresses in emails?
  4. Extract email id from text file by showing path
  5. Machine Learning Two class classification [closed]
  6. Artificial Neural Network Toplogy
  7. How to interpret data output from Weka?
  8. What is the role of the bias in neural networks? [closed]
  9. Loss & accuracy – Are these reasonable learning curves?
  10. Why do we have to normalize the input for an artificial neural network? [closed]
  11. Many to one and many to many LSTM examples in Keras
  12. How to interpret caffe log with debug_info?
  13. Caffe | solver.prototxt values setting strategy
  14. Cost function training target versus accuracy desired goal
  15. What is the difference between loss function and metric in Keras? [duplicate]
  16. TensorBoard – Plot training and validation losses on the same graph?
  17. ResNet: 100% accuracy during training, but 33% prediction accuracy with the same data
  18. Is deep learning bad at fitting simple non linear functions outside training scope (extrapolating)?
  19. How to interpret loss and accuracy for a machine learning model [closed]
  20. How to put more weight on certain features in machine learning?
  21. What is the difference between linear regression and logistic regression? [closed]
  22. Can Keras deal with input images with different size?
  23. Keras: model.evaluate vs model.predict accuracy difference in multi-class NLP task
  24. How to create caffe.deploy from train.prototxt
  25. What is the difference between Keras model.evaluate() and model.predict()?
  26. What is `lr_policy` in Caffe?
  27. Early stopping with Keras and sklearn GridSearchCV cross-validation
  28. Scikits-Learn RandomForrest trained on 64bit python wont open on 32bit python
  29. Scikit learn – fit_transform on the test set
  30. How should I teach machine learning algorithm using data with big disproportion of classes? (SVM)

Leave a Comment