CRANDEM: Conditional Random Fields for ASR

1. CRANDEM: Conditional Random Fields for ASR Jeremy Morris 11/21/2008

2. Outline • Background – Tandem HMMs & CRFs • Crandem HMM • Phone recognition • Word recognition

3. Background • Conditional Random Fields (CRFs) • Discriminative probabilistic sequence model • Directly defines a posterior probability of a label sequence given a set of observations

4. Background • Problem: How do we make use of CRF classification for word recognition? • Attempt to use CRFs directly? • Attempt to fit CRFs into current state-of-the-art models for speech recognition? • Here we focus on the latter approach • How can we integrate what we learn from the CRF into a standard HMM-based ASR system?

5. Background • Tandem HMM • Generative probabilistic sequence model • Uses outputs of a discriminative model (e.g. ANN MLPs) as input feature vectors for a standard HMM

6. Background • Tandem HMM • ANN MLP classifiers are trained on labeled speech data • Classifiers can be phone classifiers, phonological feature classifiers • Classifiers output posterior probabilities for each frame of data • E.g. P(Q|X), where Q is the phone class label and X is the input speech feature vector

7. Background • Tandem HMM • Posterior feature vectors are used by an HMM as inputs • In practice, posteriors are not used directly • Log posterior outputs or “linear” outputs are more frequently used • “linear” here means outputs of the MLP with no application of the softmax function to transform into probabilities • Since HMMs model phones as Gaussian mixtures, the goal is to make these outputs look more “Gaussian” • Additionally, Principle Components Analysis (PCA) is applied to features to decorrelate features for diagonal covariance matrices

8. Idea: Crandem • Use a CRF classifier to create inputs to a Tandem-style HMM • CRF labels provide a better per-frame accuracy than input MLPs • We’ve shown CRFs to provide better phone recognition than a Tandem system with the same inputs • This suggests that we may get some gain from using CRF features in an HMM

9. Idea: Crandem • Problem: CRF output doesn’t match MLP output • MLP output is a per-frame vector of posteriors • CRF outputs a probability across the entire sequence • Solution: Use Forward-Backward algorithm to generate a vector of posterior probabilities

10. Forward-Backward Algorithm • The Forward-Backward algorithm is already used during CRF training • Similar to the forward-backward algorithm for HMMs • Forward pass collects feature functions for the timesteps prior to the current timestep • Backward pass collects feature functions for the timesteps following the current timestep • Information from both passes are combined together to determine the probability of being in a given state at a particular timestep

11. Forward Backward Algorithm

12. Forward-Backward Algorithm • This form allows us to use the CRF to compute a vector of local posteriors y at any timestept. • We use this to generate features for a Tandem-style system • Take log features, decorelate with PCA

13. Phone Recognition • Pilot task – phone recognition on TIMIT • 61 feature MLPs trained on TIMIT, mapped down to 39 features for evaluation • Crandem compared to Tandem and a standard PLP HMM baseline model • As with previous CRF work, we use the outputs of an ANN MLP as inputs to our CRF • Various CRF models examined (state feature functions only, state+transition functions), and various input feature spaces examined (phone classifier and phonological feature classifier)

14. Phone Recognition • Phonological feature attributes • Detector outputs describe phonetic features of a speech signal • Place, Manner, Voicing, Vowel Height, Backness, etc. • A phone is described with a vector of feature values • Phone class attributes • Detector outputs describe the phone label associated with a portion of the speech signal • /t/, /d/, /aa/, etc.

15. Phone Recognition

16. Phone Recognition - Results • Phonological feature attributes • Detector outputs describe phonetic features of a speech signal • Place, Manner, Voicing, Vowel Height, Backness, etc. • A phone is described with a vector of feature values • Phone class attributes • Detector outputs describe the phone label associated with a portion of the speech signal • /t/, /d/, /aa/, etc.

17. Results (Fosler-Lussier & Morris 08) * Significantly (p<0.05) improvement at 0.6% difference between models

18. Results (Fosler-Lussier & Morris 08) * Significantly (p≤0.05) improvement at 0.6% difference between models

19. Word Recognition • Second task – Word recognition • Dictionary for word recognition has 54 distinct phones instead of 48, so new CRFs and MLPs trained to provide input features • MLPs and CRFs again trained on TIMIT to provide both phone classifier output and phonological feature classifier output • Initial experiments – use MLPs and CRFs trained on TIMIT to generate features for WSJ recognition • Next pass – use MLPs and CRFs trained on TIMIT to align label files for WSJ, then train MLPs and CRFs for WSJ recognition

20. Initial Results *Significant (p≤0.05) improvement at roughly 1% difference between models

21. Initial Results *Significant (p≤0.05) improvement at roughly 1% difference between models

22. Initial Results *Significant (p≤0.05) improvement at roughly 1% difference between models

23. Word Recognition • Problems • Some of the models show slight significant improvement over their Tandem counterpart • Unfortunately, what will cause an improvement is not yet predictable • Transition features give slight degredation when used on their own slight improvement when classifier is mixed with MFCCs • Retraining directly on WSJ data does not give improvement for CRF • Gains from CRF training are wiped away if we just retrain the MLPs on WSJ data

24. Word Recognition • Problems (cont.) • The only model that gives improvement for the Crandem system is a CRF model trained on linear outputs from MLPs • Softmax outputs – much worse than baseline • Log softmax outputs – ditto • This doesn’t seem right, especially given the results from the Crandem phone recognition experiments • These were trained on softmax outputs • I suspect “implementor error” here, though I haven’t tracked down my mistake yet

25. Word Recognition • Problems (cont.) • Because of the “linear inputs only” issue, certain features have yet to be examined fully • “Hifny”-style Gaussian scores have not provided any gain – scaling of these features may be preventing them from being useful

26. Current Work • Sort out problems with CRF models • Why is it so sensitive to the input feature type? (linear vs. log vs. softmax) • If this sensitivity is “built in” to the model, how can I appropriately scale features to include them in the model that works? • Move on to next problem – direct decoding on CRF lattices