Muutke küpsiste eelistusi

Phoneme-Based Speech Segmentation using Hybrid Soft Computing Framework 2014 ed. [Kõva köide]

,
  • Formaat: Hardback, 187 pages, kõrgus x laius: 235x155 mm, kaal: 4439 g, 62 Illustrations, color; XXI, 187 p. 62 illus. in color., 1 Hardback
  • Sari: Studies in Computational Intelligence 550
  • Ilmumisaeg: 15-Apr-2014
  • Kirjastus: Springer, India, Private Ltd
  • ISBN-10: 8132218612
  • ISBN-13: 9788132218616
Teised raamatud teemal:
  • Kõva köide
  • Hind: 95,02 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 111,79 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Phoneme-Based Speech Segmentation using Hybrid Soft Computing Framework 2014 ed.Suurem pilt
  • Formaat: Hardback, 187 pages, kõrgus x laius: 235x155 mm, kaal: 4439 g, 62 Illustrations, color; XXI, 187 p. 62 illus. in color., 1 Hardback
  • Sari: Studies in Computational Intelligence 550
  • Ilmumisaeg: 15-Apr-2014
  • Kirjastus: Springer, India, Private Ltd
  • ISBN-10: 8132218612
  • ISBN-13: 9788132218616
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9788132218616.html
Märksõnad:

The book discusses intelligent system design using soft computing and similar systems and their interdisciplinary applications. It also focuses on the recent trends to use soft computing as a versatile tool for designing a host of decision support systems.

Part I Background
1 Introduction
3(18)
1.1 Background
3(3)
1.2 Phoneme Boundary Segmentation: Present Technique
6(5)
1.3 ANN as a Speech Processing and Recognition Tool
11(4)
1.3.1 Speech Recognition Using RNN
12(2)
1.3.2 Speech Recognition Using SOM
14(1)
1.4 Motivation
15(1)
1.5 Contribution
16(1)
1.6 Organization
16(5)
References
17(4)
2 Speech Processing Technology: Basic Consideration
21(26)
2.1 Fundamentals of Speech Recognition
21(3)
2.2 Speech Communication Chain
24(4)
2.3 Mechanism of Speech Perception
28(5)
2.3.1 Physical Mechanism of Perception
28(2)
2.3.2 Perception of Sound
30(2)
2.3.3 Basic Unit of Speech Perception
32(1)
2.4 Theories and Models of Spoken Word Recognition
33(11)
2.4.1 Motor Theory of Speech Perception
35(2)
2.4.2 Analysis-by-Synthesis Model
37(1)
2.4.3 Direct Realist Theory of Speech Perception
37(1)
2.4.4 Cohort Theory
38(2)
2.4.5 Trace Model
40(2)
2.4.6 Shortlist Model
42(1)
2.4.7 Neighborhood Activation Model
43(1)
2.5 Conclusion
44(3)
References
44(3)
3 Fundamental Considerations of ANN
47(30)
3.1 Introduction
47(3)
3.2 Learning Strategy
50(2)
3.3 Prediction and Classification Using ANN
52(1)
3.4 Multi Layer Perceptron
53(2)
3.5 Recurrent Neural Network
55(8)
3.6 Probabilistic Neural Network
63(3)
3.6.1 Architecture of a PNN Network
64(2)
3.7 Self-Organizing Map
66(5)
3.7.1 Competitive Learning and Self-Organizing Map (SOM)
69(2)
3.8 Learning Vector Quantization
71(3)
3.8.1 LVQ Approach
72(1)
3.8.2 LVQ Algorithm
72(2)
3.9 Conclusion
74(3)
References
74(3)
4 Sounds of Assamese Language
77(18)
4.1 Introduction
77(1)
4.2 Formation of Assamese Language
78(1)
4.3 Phonemes of Assamese Language
79(12)
4.3.1 Vowels
80(4)
4.3.2 Diphthongs
84(1)
4.3.3 Stop Consonant
84(2)
4.3.4 Nasals
86(2)
4.3.5 Fricatives
88(1)
4.3.6 Affricates
89(1)
4.3.7 Semi Vowels
90(1)
4.4 Some Specific Phonemical Features of Assamese Language
91(1)
4.5 Dialects of Assamese Language
92(1)
4.6 Conclusion
92(3)
References
92(3)
5 State of Research of Speech Recognition
95(22)
5.1 Introduction
95(2)
5.2 A Brief Overview of Speech Recognition Technology
97(1)
5.3 Review of Speech Recognition During the Last Two Decades
98(3)
5.4 Research of Speech Recognition in Indian Languages
101(8)
5.4.1 Statistical Approach
102(4)
5.4.2 ANN-Based Approach
106(3)
5.5 Conclusion
109(8)
References
109(8)
Part II Design Aspects
6 Phoneme Segmentation Technique Using Self-Organizing Map (SOM)
117(20)
6.1 Introduction
117(1)
6.2 Linear Prediction Coefficient (LPC) as Speech Feature
118(1)
6.3 Application of SOM and PNN for Phoneme Boundary Segmentation
119(2)
6.4 DWT-Based Speech Segmentation
121(2)
6.5 Proposed SOM- and PNN-Based Segmentation Algorithm
123(3)
6.5.1 PNN Learning Algorithm
124(1)
6.5.2 SOM Weight Vector Extraction Algorithm
125(1)
6.5.3 PNN-Based Decision Algorithm
125(1)
6.6 Experimental Details and Result
126(8)
6.6.1 Experimental Speech Signals
126(1)
6.6.2 Preprocessing
127(2)
6.6.3 Role of PNN Smoothing Parameter
129(3)
6.6.4 Comparison of SOM- and DWT-Based Segmentation
132(2)
6.7 Conclusion
134(3)
References
135(2)
7 Application of Phoneme Segmentation Technique in Spoken Word Recognition
137(16)
7.1 Introduction
137(2)
7.2 Linear Prediction Model for Estimation of Formant Frequency
139(3)
7.2.1 Human Vocal Tract and Linear Prediction Model of Speech
140(2)
7.2.2 Pole or Formant Location Determination
142(1)
7.3 LVQ and Its Application to Codebook Design
142(1)
7.4 Phoneme Segmentation for Spoken Word Recognition
143(3)
7.4.1 RNN-Based Local Classification
144(1)
7.4.2 SOM-Based Segmentation Algorithm
145(1)
7.4.3 PNN- and Fl-Based Vowel Phoneme and Initial Phoneme Recognition
145(1)
7.4.4 LVQ Codebook Assisted Last Phoneme Recognition
146(1)
7.5 Experimental Details and Results
146(5)
7.5.1 Experimental Speech Signals
148(1)
7.5.2 RNN Training Consideration
148(2)
7.5.3 Phoneme Segmentation and Classification Results
150(1)
7.6 Conclusion
151(2)
References
152(1)
8 Application of Clustering Techniques to Generate a Priori Knowledge for Spoken Word Recognition
153(10)
8.1 Introduction
153(1)
8.2 K-Means Clustering (KMC)
154(1)
8.3 KMC Applied to Speech Data
155(2)
8.4 Experimental Work
157(4)
8.4.1 Experimental Speech Samples
157(1)
8.4.2 Role of RNN in Decision Making of the Proposed Technique
158(1)
8.4.3 Result and Limitation
159(2)
8.5 Conclusion
161(2)
References
162(1)
9 Application of Proposed Phoneme Segmentation Technique for Speaker Identification
163(20)
9.1 Introduction
163(2)
9.2 Certain Previous Work Done
165(4)
9.3 Linear Prediction Residual Feature
169(1)
9.4 EMD Residual-Based Source Extraction
169(1)
9.5 LVQ Codebook and Speaker Identification
170(1)
9.6 Speaker Database
170(1)
9.7 Experimental Details and Results
171(1)
9.8 System Description
171(9)
9.8.1 Vowel Segmentation Results
172(2)
9.8.2 Speaker Identification Results Using LP Residual
174(2)
9.8.3 Speaker Identification Results Using EMD Residual
176(4)
9.9 Conclusion
180(3)
References
180(3)
10 Conclusion
183(2)
10.1 Conclusion
183(1)
10.2 Limitation
184(1)
10.3 Future Scope
184(1)
Index 185
Ms. Mousmita Sarma is currently working as Research Consultant at M/s. SpeecHWareNet Pvt. (I) Ltd., Technology Incubation Center, IIT Guwahati, Assam, India. She completed MSc in Electronics and Communication Technology from Gauhati University, India in 2010. She also completed M.Tech from the same institution in 2012 with specialization in Speech Processing and Recognition. She has co-authored one book and published several peer reviewed research papers in international conference proceedings and journals. She serves as reviewer to several journals and IEEE international and national conferences. Her areas of interest include Speech Recognition, soft-Computation and HCI Applications.

Dr. Kandarpa Kumar Sarma, currently Associate Professor in Department of Electronics and Communication Technology, Gauhati University, Guwahati, Assam, India, has over seventeen years of professional experience. He has covered all areas of UG/PG level electronics courses including soft computing, mobile communication, digital signal and image processing. He obtained M.Tech degree in Signal Processing from Indian Institute of Technology Guwahati in 2005 and subsequently completed PhD programme in the area of Soft-Computational Application in Mobile Communication. He has authored six books, several book chapters, around three hundred peer reviewed research papers in international conference proceedings and journals. His areas of interest are Soft-Computation and its Applications, Mobile Communication, Antenna Design, Speech Processing, Document Image Analysis and Signal Processing Applications in High Energy Physics, Neuro-computing and Computational Models for Social-Science Applications. He is senior member IEEE (USA), Fellow IETE (India), Member International Neural Network Society (INNS, USA), Life Member ISTE (India) and Life Member CSI (India). He serves as an Editor-in-Chief of International Journal of Intelligent System Design and Computing (IJISDC, UK), guesteditor of several international journals, reviewer of over thirty international journals and over hundred international conferences.