Force Alignment using HMM 2

This is the continuation of the post before. This discussion on this post is:

  1. The variation of accuracy and correctness based on the number of observation mixtures.
  2. How does adding noise affect our recognition accuracy (The experiment done in our last post involves clean test input)
  3. The confusion matrix of our test results

 

 

Correctness and Accuracy vs Insertion

Clean

clean_acc.png

Subway Noise (SNR=10dB)

subway_10db.png.png

White Noise (SNR=10dB)

white_10_acc

White Noise (SNR=20dB)

white_20_acc.png

It can be observed that the test signal with additive Subway noise performs the worst here due to its non-interpretability compared to additive white noise.

Correctness and Accuracy vs Number of Mixtures

This experiment is done with insertion penalty of -60 (s=-60 of HVite)

Clean

clean_mix.png

Subway Noise (SNR=10dB)

subway_mix

White Noise (SNR=10dB)

white_10_mix

White Noise (SNR=20dB)

white_20_mix.png

As expected, additive subway noise performs the worst here.

Confusion Matrix

Selection_019.png

Reading across the rows, %c indicates the number of correct instances divided by the total number of instances in the row. %e is the number of incorrect instances in the row divided by the total number of instances (N).

It can be observed that the word that is the misclassified most of the time is “yi” which is often classified as “ling”. In physical sense, the “e” sound in both is really similar which explains the high misclassificaiton rate.

The second word that performs badly here is “liu” which is misclassified as “jiu”. The reason of this is because they share the same phone “iu” at the back.

 

Advertisements

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s