投影片 1

投影片 1 (Lab531, 1:20:43)

00:13
1. Speech Production and Source Model
00:18
2. Waveform plots of typical vowel sounds - Voiced（濁音）
00:29
3. Speech Production and Source Model
00:40
4. Slide 4
00:06
5. Waveform plots of typical consonant sounds
00:19
6. Slide 4
00:08
7. Speech Production and Source Model
00:20
8. Slide 4
00:05
9. Speech Production and Source Model
00:06
10. Waveform plots of typical vowel sounds - Voiced（濁音）
00:01
11. Speech Production and Source Model
00:01
12. Slide 4
00:01
13. Waveform plots of typical consonant sounds
00:19
14. Waveform plot of a sentence
01:24
15. Time and Frequency Domains (P.12 of 2.0)
00:15
16. Frequency domain spectra of speech signals
00:33
17. Frequency Domain
00:05
18. Frequency domain spectra of speech signals
00:01
19. Time and Frequency Domains (P.12 of 2.0)
00:01
20. Waveform plot of a sentence
00:01
21. Waveform plots of typical consonant sounds
00:06
22. Slide 4
00:01
23. Waveform plots of typical consonant sounds
00:01
24. Waveform plot of a sentence
00:01
25. Time and Frequency Domains (P.12 of 2.0)
00:08
26. Frequency domain spectra of speech signals
00:04
27. Frequency Domain
01:53
28. Input/Output Relationship for Time/Frequency Domains
00:16
29. Spectrogram
00:04
30. Spectrogram
00:17
31. Formant Frequencies
00:06
32. Formant frequency contours
00:03
33. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
00:07
34. Slide 16
00:30
35. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
00:02
36. Slide 16
00:04
37. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
00:01
38. Slide 16
00:03
39. Speech Source Model
00:05
40. Simplified Speech Source Model
00:19
41. Speech Source Model
04:00
42. Feature Extraction - MFCC
02:08
43. Pre-emphasis
00:09
44. Feature Extraction - MFCC
00:02
45. Pre-emphasis
00:17
46. Why pre-emphasis?
00:16
47. Pre-emphasis
00:01
48. Feature Extraction - MFCC
00:01
49. Speech Source Model
00:01
50. Simplified Speech Source Model
00:01
51. Speech Source Model
00:01
52. Slide 16
00:01
53. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
00:01
54. Formant frequency contours
00:01
55. Formant Frequencies
00:01
56. Spectrogram
00:01
57. Spectrogram
00:01
58. Input/Output Relationship for Time/Frequency Domains
00:04
59. Frequency Domain
00:13
60. Frequency domain spectra of speech signals
00:04
61. Frequency Domain
00:01
62. Input/Output Relationship for Time/Frequency Domains
00:01
63. Spectrogram
00:01
64. Spectrogram
00:01
65. Formant Frequencies
00:01
66. Formant frequency contours
00:01
67. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
00:01
68. Slide 16
00:01
69. Speech Source Model
00:01
70. Simplified Speech Source Model
00:01
71. Speech Source Model
00:01
72. Feature Extraction - MFCC
00:03
73. Pre-emphasis
00:37
74. Why pre-emphasis?
00:06
75. Why Windowing?
00:37
76. Waveform plot of a sentence
00:47
77. Why Windowing?
00:12
78. Waveform plot of a sentence
00:59
79. Why Windowing?
00:02
80. Waveform plot of a sentence
01:55
81. Slide 25
00:12
82. Waveform plot of a sentence
00:05
83. Slide 25
01:08
84. Effect of Windowing (1)
00:57
85. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
03:42
86. Windowing
00:02
87. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
00:04
88. Effect of Windowing (1)
00:01
89. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
00:01
90. Windowing
00:18
91. Effect of Windowing (2)
00:59
92. Windowing
00:51
93. Effect of Windowing (2)
00:01
94. Windowing
00:01
95. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
00:02
96. Effect of Windowing (1)
00:24
97. Slide 25
00:01
98. Waveform plot of a sentence
00:01
99. Slide 25
00:59
100. Effect of Windowing (1)
00:02
101. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
00:04
102. Windowing
00:02
103. Effect of Windowing (2)
00:30
104. DFT and Mel-filter-bank Processing
01:25
105. Peripheral Processing for Human Perception
00:24
106. Mel-scale Filter Bank
00:16
107. Peripheral Processing for Human Perception
00:50
108. Mel-scale Filter Bank
00:02
109. Peripheral Processing for Human Perception
00:04
110. DFT and Mel-filter-bank Processing
00:01
111. Peripheral Processing for Human Perception
00:01
112. Mel-scale Filter Bank
05:35
113. Why Filter-bank Processing?
00:02
114. Mel-scale Filter Bank
00:02
115. Peripheral Processing for Human Perception
00:16
116. DFT and Mel-filter-bank Processing
00:01
117. Peripheral Processing for Human Perception
00:35
118. Mel-scale Filter Bank
00:01
119. Peripheral Processing for Human Perception
02:18
120. DFT and Mel-filter-bank Processing
00:01
121. Peripheral Processing for Human Perception
00:05
122. Mel-scale Filter Bank
00:03
123. Why Filter-bank Processing?
00:15
124. Feature Extraction - MFCC
01:56
125. Logarithmic Operation and IDFT
00:21
126. Why Log Energy Computation?
00:25
127. Logarithmic Operation and IDFT
01:11
128. Why Log Energy Computation?
00:15
129. Logarithmic Operation and IDFT
03:48
130. Why Log Energy Computation?
00:07
131. Logarithmic Operation and IDFT
00:03
132. Why Log Energy Computation?
00:35
133. Why Inverse DFT?
00:01
134. Why Log Energy Computation?
00:20
135. Logarithmic Operation and IDFT
00:01
136. Why Log Energy Computation?
02:28
137. Why Inverse DFT?
00:19
138. Why Log Energy Computation?
00:01
139. Logarithmic Operation and IDFT
00:01
140. Feature Extraction - MFCC
00:01
141. Why Filter-bank Processing?
00:01
142. Mel-scale Filter Bank
00:01
143. Peripheral Processing for Human Perception
00:01
144. DFT and Mel-filter-bank Processing
00:01
145. Effect of Windowing (2)
00:01
146. Windowing
00:56
147. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
00:01
148. Windowing
00:01
149. Effect of Windowing (2)
00:01
150. DFT and Mel-filter-bank Processing
00:01
151. Peripheral Processing for Human Perception
00:01
152. Mel-scale Filter Bank
00:01
153. Why Filter-bank Processing?
00:01
154. Feature Extraction - MFCC
00:01
155. Logarithmic Operation and IDFT
00:34
156. Why Log Energy Computation?
00:19
157. Why Inverse DFT?
00:08
158. Speech Production and Source Model (P.3 of 7.0)
00:02
159. Slide 39
00:01
160. Frequency domain spectra of speech signals (P.8 of 7.0)
00:01
161. Frequency Domain (P.9 of 7.0)
00:02
162. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
01:46
163. Slide 43
00:01
164. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
00:01
165. Frequency Domain (P.9 of 7.0)
00:01
166. Frequency domain spectra of speech signals (P.8 of 7.0)
00:01
167. Slide 39
00:01
168. Speech Production and Source Model (P.3 of 7.0)
00:01
169. Why Inverse DFT?
00:01
170. Why Log Energy Computation?
01:07
171. Logarithmic Operation and IDFT
00:05
172. Why Log Energy Computation?
00:29
173. Why Inverse DFT?
00:01
174. Why Log Energy Computation?
00:01
175. Logarithmic Operation and IDFT
00:01
176. Feature Extraction - MFCC
00:24
177. Why Filter-bank Processing?
00:01
178. Feature Extraction - MFCC
00:01
179. Logarithmic Operation and IDFT
00:01
180. Why Log Energy Computation?
00:01
181. Why Inverse DFT?
00:01
182. Speech Production and Source Model (P.3 of 7.0)
00:01
183. Slide 39
00:01
184. Frequency domain spectra of speech signals (P.8 of 7.0)
00:01
185. Frequency Domain (P.9 of 7.0)
00:01
186. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
00:01
187. Slide 43
00:02
188. Derivatives
00:11
189. Slide 43
00:41
190. Slide 43
01:07
191. Derivatives
01:08
192. (xi, yi)
00:13
193. Derivatives
00:53
194. (xi, yi)
00:52
195. Derivatives
00:02
196. Slide 43
00:01
197. Derivatives
00:12
198. (xi, yi)
00:01
199. Why Delta Coefficients?
00:01
200. (xi, yi)
00:32
201. Derivatives
00:01
202. (xi, yi)
00:32
203. Why Delta Coefficients?
00:03
204. (xi, yi)
00:08
205. Why Delta Coefficients?
00:01
206. (xi, yi)
00:02
207. Derivatives
00:09
208. (xi, yi)
00:20
209. Why Delta Coefficients?
02:33
210. Slide 47
00:30
211. Why Delta Coefficients?
00:16
212. Slide 47
00:25
213. Why Delta Coefficients?
00:01
214. Slide 47
00:13
215. End-point Detection
01:37
216. End-point Detection
01:37
217. End-point Detection
00:01
218. Slide 47
00:01
219. End-point Detection
01:27
220. End-point Detection
00:33
221. End-point Detection
00:10
222. End-point Detection
01:23
223. End-point Detection
00:01
224. End-point Detection
00:53
225. 與語音學、訊號波型、頻譜特性有關的網址

1. Speech Production and Source Model
2. Waveform plots of typical vowel sounds - Voiced（濁音）
3. Speech Production and Source Model
4. Slide 4
5. Waveform plots of typical consonant sounds
6. Slide 4
7. Speech Production and Source Model
8. Slide 4
9. Speech Production and Source Model
10. Waveform plots of typical vowel sounds - Voiced（濁音）
11. Speech Production and Source Model
12. Slide 4
13. Waveform plots of typical consonant sounds
14. Waveform plot of a sentence
15. Time and Frequency Domains (P.12 of 2.0)
16. Frequency domain spectra of speech signals
17. Frequency Domain
18. Frequency domain spectra of speech signals
19. Time and Frequency Domains (P.12 of 2.0)
20. Waveform plot of a sentence
21. Waveform plots of typical consonant sounds
22. Slide 4
23. Waveform plots of typical consonant sounds
24. Waveform plot of a sentence
25. Time and Frequency Domains (P.12 of 2.0)
26. Frequency domain spectra of speech signals
27. Frequency Domain
28. Input/Output Relationship for Time/Frequency Domains
29. Spectrogram
30. Spectrogram
31. Formant Frequencies
32. Formant frequency contours
33. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
34. Slide 16
35. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
36. Slide 16
37. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
38. Slide 16
39. Speech Source Model
40. Simplified Speech Source Model
41. Speech Source Model
42. Feature Extraction - MFCC
43. Pre-emphasis
44. Feature Extraction - MFCC
45. Pre-emphasis
46. Why pre-emphasis?
47. Pre-emphasis
48. Feature Extraction - MFCC
49. Speech Source Model
50. Simplified Speech Source Model
51. Speech Source Model
52. Slide 16
53. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
54. Formant frequency contours
55. Formant Frequencies
56. Spectrogram
57. Spectrogram
58. Input/Output Relationship for Time/Frequency Domains
59. Frequency Domain
60. Frequency domain spectra of speech signals
61. Frequency Domain
62. Input/Output Relationship for Time/Frequency Domains
63. Spectrogram
64. Spectrogram
65. Formant Frequencies
66. Formant frequency contours
67. Voiced/unvoiced濁音、清音Pitch/tone音高、聲調Vocal tract 聲道Frequency domain/formant frequencySpectrogram representationSpeech Source Model
68. Slide 16
69. Speech Source Model
70. Simplified Speech Source Model
71. Speech Source Model
72. Feature Extraction - MFCC
73. Pre-emphasis
74. Why pre-emphasis?
75. Why Windowing?
76. Waveform plot of a sentence
77. Why Windowing?
78. Waveform plot of a sentence
79. Why Windowing?
80. Waveform plot of a sentence
81. Slide 25
82. Waveform plot of a sentence
83. Slide 25
84. Effect of Windowing (1)
85. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
86. Windowing
87. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
88. Effect of Windowing (1)
89. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
90. Windowing
91. Effect of Windowing (2)
92. Windowing
93. Effect of Windowing (2)
94. Windowing
95. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
96. Effect of Windowing (1)
97. Slide 25
98. Waveform plot of a sentence
99. Slide 25
100. Effect of Windowing (1)
101. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
102. Windowing
103. Effect of Windowing (2)
104. DFT and Mel-filter-bank Processing
105. Peripheral Processing for Human Perception
106. Mel-scale Filter Bank
107. Peripheral Processing for Human Perception
108. Mel-scale Filter Bank
109. Peripheral Processing for Human Perception
110. DFT and Mel-filter-bank Processing
111. Peripheral Processing for Human Perception
112. Mel-scale Filter Bank
113. Why Filter-bank Processing?
114. Mel-scale Filter Bank
115. Peripheral Processing for Human Perception
116. DFT and Mel-filter-bank Processing
117. Peripheral Processing for Human Perception
118. Mel-scale Filter Bank
119. Peripheral Processing for Human Perception
120. DFT and Mel-filter-bank Processing
121. Peripheral Processing for Human Perception
122. Mel-scale Filter Bank
123. Why Filter-bank Processing?
124. Feature Extraction - MFCC
125. Logarithmic Operation and IDFT
126. Why Log Energy Computation?
127. Logarithmic Operation and IDFT
128. Why Log Energy Computation?
129. Logarithmic Operation and IDFT
130. Why Log Energy Computation?
131. Logarithmic Operation and IDFT
132. Why Log Energy Computation?
133. Why Inverse DFT?
134. Why Log Energy Computation?
135. Logarithmic Operation and IDFT
136. Why Log Energy Computation?
137. Why Inverse DFT?
138. Why Log Energy Computation?
139. Logarithmic Operation and IDFT
140. Feature Extraction - MFCC
141. Why Filter-bank Processing?
142. Mel-scale Filter Bank
143. Peripheral Processing for Human Perception
144. DFT and Mel-filter-bank Processing
145. Effect of Windowing (2)
146. Windowing
147. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
148. Windowing
149. Effect of Windowing (2)
150. DFT and Mel-filter-bank Processing
151. Peripheral Processing for Human Perception
152. Mel-scale Filter Bank
153. Why Filter-bank Processing?
154. Feature Extraction - MFCC
155. Logarithmic Operation and IDFT
156. Why Log Energy Computation?
157. Why Inverse DFT?
158. Speech Production and Source Model (P.3 of 7.0)
159. Slide 39
160. Frequency domain spectra of speech signals (P.8 of 7.0)
161. Frequency Domain (P.9 of 7.0)
162. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
163. Slide 43
164. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
165. Frequency Domain (P.9 of 7.0)
166. Frequency domain spectra of speech signals (P.8 of 7.0)
167. Slide 39
168. Speech Production and Source Model (P.3 of 7.0)
169. Why Inverse DFT?
170. Why Log Energy Computation?
171. Logarithmic Operation and IDFT
172. Why Log Energy Computation?
173. Why Inverse DFT?
174. Why Log Energy Computation?
175. Logarithmic Operation and IDFT
176. Feature Extraction - MFCC
177. Why Filter-bank Processing?
178. Feature Extraction - MFCC
179. Logarithmic Operation and IDFT
180. Why Log Energy Computation?
181. Why Inverse DFT?
182. Speech Production and Source Model (P.3 of 7.0)
183. Slide 39
184. Frequency domain spectra of speech signals (P.8 of 7.0)
185. Frequency Domain (P.9 of 7.0)
186. Input/Output Relationship for Time/Frequency Domains (P.10 of 7.0)
187. Slide 43
188. Derivatives
189. Slide 43
190. Slide 43
191. Derivatives
192. (xi, yi)
193. Derivatives
194. (xi, yi)
195. Derivatives
196. Slide 43
197. Derivatives
198. (xi, yi)
199. Why Delta Coefficients?
200. (xi, yi)
201. Derivatives
202. (xi, yi)
203. Why Delta Coefficients?
204. (xi, yi)
205. Why Delta Coefficients?
206. (xi, yi)
207. Derivatives
208. (xi, yi)
209. Why Delta Coefficients?
210. Slide 47
211. Why Delta Coefficients?
212. Slide 47
213. Why Delta Coefficients?
214. Slide 47
215. End-point Detection
216. End-point Detection
217. End-point Detection
218. Slide 47
219. End-point Detection
220. End-point Detection
221. End-point Detection
222. End-point Detection
223. End-point Detection
224. End-point Detection
225. 與語音學、訊號波型、頻譜特性有關的網址

0/225

Volume

1.0x

00:00/1:20:43