Dynamic Time Warping fixed - frame coefficient with pitch feature for speech recognition system with neural network

dc.contributor.authorSudirman, Rubita
dc.date.accessioned2024-12-18T01:23:52Z
dc.date.available2024-12-18T01:23:52Z
dc.date.issued2007
dc.descriptionThesis Ph.D (Civil Engineering)
dc.description.abstractAutomatic Speech Recognition products are already available in the market since many years ago. Intensive research and development still continue for further improvement of speech technology. Among typical methods that have been applied to speech technology are Hidden Markov Model (HMM), Dynamic Time Warping (DTW), and Neural Network (NN). However previous research relied heavily on the HMM without paying much attention to Neural Network (NN). In this research, NN with back-propagation algorithm is used to perform the recognition, with inputs derived from Linear Predictive Coefficient (LPC) and pitch feature. It is known that back-propagation NN is capable of handling large learning problems and is a very promising method due to its ability to train data and classify them. NN has not been fully employed as a successful speech recognition engine since it requires a normalized input length. The nonlinear time normalization based on DTW is identified as the suitable tool to overcome time variation problem by expanding or compressing the speech to a desired number of data. The proposed DTW frame fixing (DTW-FF) algorithm is an extended DTW algorithm to reduce the number of inputs into the NN. This method had reduced the amount of computation and network complexity by reducing the number of inputs by 90%. Therefore a faster recognition is achieved. Recognition using DTW showed the same results when LPC or DTW-FF feature were used. This indicates no loss of information occurred during data manipulation. Pitch estimate is another feature introduced to the NN that has helped to increase recognition accuracy. An average of 10.32% improvement is recorded when pitch is added to DTW-FF feature as input to back-propagation NN using Malay digits samples. The back-propagation algorithm was then designed with both the Quasi Newton and Conjugate Gradient methods. This is to compare which method is able to achieve optimal global minimum. Results showed that Conjugate Gradient performed better.
dc.description.sponsorshipUniversity Technology Malaysia
dc.identifier.urihttps://openscience.utm.my/handle/123456789/1515
dc.language.isoen
dc.publisherUniversity Technology Malaysia
dc.subjectAutomatic speech recognition
dc.subjectBack propagation (Artificial intelligence)
dc.subjectNeural networks (Computer science)
dc.titleDynamic Time Warping fixed - frame coefficient with pitch feature for speech recognition system with neural network
dc.typeThesis
dc.typeDataset
Files
Original bundle
Now showing 1 - 4 of 4
Loading...
Thumbnail Image
Name:
RubitaSudirmanPFKA2007_A.pdf
Size:
90.67 KB
Format:
Adobe Portable Document Format
Description:
Transfer Function
Loading...
Thumbnail Image
Name:
RubitaSudirmanPFKA2007_B.pdf
Size:
286.96 KB
Format:
Adobe Portable Document Format
Description:
Pitch-Scaled Harmonic Filter (PSHF) User Manual
Loading...
Thumbnail Image
Name:
RubitaSudirmanPFKA2007_C.pdf
Size:
89.25 KB
Format:
Adobe Portable Document Format
Description:
Experimental Results
Loading...
Thumbnail Image
Name:
RubitaSudirmanPFKA2007_D.pdf
Size:
93.43 KB
Format:
Adobe Portable Document Format
Description:
Source code for Quasi Newton and Conjugate Gradient descent algorithm
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description: