DTW

1
??? ??? ?? ?? ?? DTW ????

• Yong-Sun Choi and Soo-Young Lee
• Brain Science Research Center and
• Department of Electrical Engineering and Computer
  Science
• Korea Advanced Institute of Science and Technology

2
Contents

• Keyword Spotting
• Meaning Necessity
• Problems
• Dynamic Time Warping (DTW)
• Advantages of DTW
• Some conventional types Proposed DTW type
• Experimental Results
• Verification of proposed DTW performance
• Standard threshold setting
• Results of various conditions
• Conclusions

3
Keyword Spotting

• Meaning
• Detection of pre-defined keywords in the
  continuous speech
• Example)
• Keywords open, window
• Input umokay, uh please open theuhwindow
• Necessity
• Human may say OOV(Out Of Vocabulary), sometimes
  stammer
• But machine only needs some specific words for
  recognition

4
Problems Goal

• Difficulties
• of process
• End-Point-Detection of speech segment
• Rejection of OOVs
• of implementation
• A big load of calculations
• Complex algorithm
• Hard to build up a real hardware system
• Goal
• Simple Fast Algorithm

5
DTW for Keyword Spotting

• Hidden Markov Model (HMM)
• A statistical model need large number of datum
  for training
• Complex algorithm hard to implement a hardware
  system
• Many parameters can cause memory problem
• Dynamic Time Warping (DTW)
• Advantages
• Small number of datum for training
• Simple algorithm (addition multiplication)
• Small number of stored datum
• Weak points
• Need EPD process, Many calculations

6
General DTW Process

• Known both End Points
• Repetition of searches
• Finding corresponding frames

7
Advanced DTW

• Myers, Rabiner and Rosenberg
• No EPD Process
• Series of small area searches
• Global search in one area
• Setting next area around the best match point of
  local area
• Reducing amount of calculations but still much
• Tested in isolated word recognition

8
Proposal Shape Weights

• No EPD process
• Only one path
• Select the best match point and search again at
  the point
• Less computations
• Modifying weights
• To compensate weight-sum differences
• For search
• For distance accumulation

9
Proposal End Point

• Small search area
• Successive local searches
• Start search at one point
• End condition
• When the point is on the last frame of Ref.
  pattern
• Setting up End Point automatically

10
Proposal Distance

• Modifying distance
• Using differences of pattern lengths
• Pattern lengths of same words are similar each
  other

11
DTW Computation Loads

• 3 types

12
Data Base EX-SET

• DB
• RoadRally
• For keyword spotting
• Based on telephone channel
• Usages
• 11 keywords (Total 434 occurrences)
• 40 male speakers read speech (Total 47 min.) in
  Stonehenge
• SET construction
• 4 sub-set (about 108 keywords / set)
• 3 set for training , 1 set for test
• 2 reference patterns / keyword / set

13
Verification Result

• Isolated Word Recognition
• 3 set for training , 1 set for test

14
Experimental Setup

• Assumption
• Any frame can be the last frame of keywords
• Threshold
• To reject OOV
• 1 threshold / ref.
• Standard threshold no false alarm in training
  set
• Result presentation
• ROC (Receiver Operator Characteristic)
• X-axis false alarm / hour / keyword
• Y-axis recognition rate

15
Thresholds Setting Recognition Rate of
Training Set

• Training set Test set (No false alarm)

16
Result DTW HMM

• ROC Curve

17
Changing Conditions
No. of Keywords
No. of References
18
Conclusion

• Proposed DTW
• Advantages
• Simple structure addition multiplication
  (good for hardware)
• No EPD processing
• Very small computation load
• Small stored datum small memory
• Only keyword information
• Good performance
• Keyword Spotting
• Better than HMM in the case of small training
  datum