ISCSLP Tutorial 2 - 版本历史

2014年9月13日 (六) 07:05 Cslt

2014-09-13T07:05:04Z

2014-09-13T07:02:15Z

2014-09-13T06:56:08Z

2014-09-13T06:38:26Z

2014-09-13T05:57:41Z

2014-09-13T05:25:58Z

2014-09-13T05:15:16Z

以“Prof. Chung-Hsien Arousal & Valence coordinator”为内容创建页面

新页面

Prof. Chung-Hsien

Arousal & Valence coordinator

←上一版本		2014年9月13日 (六) 07:05的版本
第97行：		第97行：
	:* Glottal features		:* Glottal features
	:* SDC: a more logn-gap mfcc data, quite similar to delta_MFCC, however long shift		:* SDC: a more logn-gap mfcc data, quite similar to delta_MFCC, however long shift
		+	* Future: relationship between cognitive load vs arousal; mutimodal data, improve discrimination, test under less constrained conditions

←上一版本		2014年9月13日 (六) 07:02的版本
第96行：		第96行：
	:* load measure: analytical measure (number of ++); physical measure: EEG, ECG/HRV, GSR, respiration; task measure: speech, drawing...		:* load measure: analytical measure (number of ++); physical measure: EEG, ECG/HRV, GSR, respiration; task measure: speech, drawing...
	:* Glottal features		:* Glottal features
		+	:* SDC: a more logn-gap mfcc data, quite similar to delta_MFCC, however long shift

@@ 第80行： / 第80行： @@
 :* this can be reverse
-Emotion variability, by Prof.  Julien Epps:
+Emotion variability, by Prof.  Vidhyasaharan Sethu:
 * GMM supervector  based emotion
@@ 第86行： / 第86行： @@
 :* remove phone variability by phone dependent GMMs
 :* speaker normalization is important for emotion recognition
-:* two ways: speaker adaptation & speaker signal normalization
+:* two ways: speaker adaptation & speaker signal
 :* KL-based estimation on speaker and emotion variability
 :* speaker normalization by feature warping
 ''':* speaker variation modeling with JFA'''
 :* Speaker adaptation : speaker library
 :*

@@ 第68行： / 第68行： @@
 * Music information retrieval  (MIR)
 :* title search
-:* search by query
+:* search by query:
 :* emotion of songs labelled by persons forms a Gaussian
 :* represent the aoustic features of a song by a probabilistic history vector
 :* acoustic GMM posterior representation as a feature
 :* GMM code book constructed in training (VA GMM)

@@ 第22行： / 第22行： @@
 :* temporal information is obtained
 :* difficult to model context well
-:* a large number of local features need to be extracted
+:* a large number of local features need to be extracted,
 * Unit choice for dynamic modeling
@@ 第28行： / 第28行： @@
 :* meaningful unit: word, syllable, phrases
 :* emotionally consistent unit: emotion profiles, emotograms
-recognition models
+* recognition models

←上一版本		2014年9月13日 (六) 05:25的版本
第1行：		第1行：
	Prof. Chung-Hsien		Prof. Chung-Hsien

−	Arousal & Valence coordinator	+	* Arousal & Valence coordinator
		+	* separate emotion process to sub emotions
		+
		+	* available databases:
		+	* database collection:
		+	:* acted : GEneva multimodeal emotion portrayals (GEMEP)
		+	:* induced : eNTERFACE'05 EMOTION Database
		+	:* spontaneous: SEMAINE, AFEW
		+	: others: RML,VAM ,FAU AUBO,SAVEE,TUMAVIC,IEMOCAP,SEMAINE MHMC
		+
		+	* static vs dynamic modeling
		+
		+	STATIC:
		+	:* low level descriptors (LLDs) and functionals
		+	:* good for discriminate high and low-arousal emotions
		+	:* temporal information is lost, no suitable for long utterances, can not detect change in emotion
		+
		+	DYNAMIC:
		+	:* frame as the basis, LLDs are extracted and modeled by GMMs, HMMs, DTW
		+	:* temporal information is obtained
		+	:* difficult to model context well
		+	:* a large number of local features need to be extracted
		+
		+	* Unit choice for dynamic modeling
		+	:* technical unit: frame, time slice, equally-divided unit
		+	:* meaningful unit: word, syllable, phrases
		+	:* emotionally consistent unit: emotion profiles, emotograms
		+
		+
		+
		+	recognition models