News-20150401 - 版本历史

2015年5月15日 (五) 11:40 Cslt

2015-05-15T11:40:00Z

2015年5月15日 (五) 11:39 Cslt

2015-05-15T11:39:46Z

2015年4月3日 (五) 02:05 Cslt

2015-04-03T02:05:40Z

2015年4月3日 (五) 02:05 Cslt

2015-04-03T02:05:31Z

2015年4月3日 (五) 02:04 Cslt

2015-04-03T02:04:55Z

2015年4月3日 (五) 02:04 Cslt

2015-04-03T02:04:31Z

2015年4月3日 (五) 02:03 Cslt

2015-04-03T02:03:42Z

2015年4月3日 (五) 02:03 Cslt

2015-04-03T02:03:22Z

2015年4月3日 (五) 02:02 Cslt

2015-04-03T02:02:30Z

Cslt：以“Time: 2015/03/30 10AM Venue: FIT BLDG, 1-315 Speech structure; human-inspired representation of speech acoustics — What are "really" speaker-independent features...”为内容创建页面

2015-04-03T02:00:35Z

以“Time: 2015/03/30 10AM Venue: FIT BLDG, 1-315 Speech structure; human-inspired representation of speech acoustics — What are "really" speaker-independent features...”为内容创建页面

新页面

Time: 2015/03/30 10AM
Venue: FIT BLDG, 1-315

Speech structure; human-inspired representation of speech acoustics
— What are "really" speaker-independent features? —

Speech signals covey various kinds of information, which are broadly grouped into two kinds, linguistic and extra-linguistic information. Many speech applications, however, focus on only a single aspect of speech. For example, speech recognizers try to extract only word identity from speech signals and speaker recognizers extract only speaker identity. Here, irrelevant aspects are often treated as hidden or latent by applying the probability theory to a large number of samples or the irrelevant aspects are normalized to have quasi-standard values. In speech analysis, however, phases are usually removed, not hidden or normalized, and pitch harmonics are also removed, not hidden or normalized. The resulting speech spectrum still contains both linguistic (word identity) and extra‐linguistic information (speaker identity). Is there any good method to remove extra-linguistic information from the spectrum? In this talk, our proposal of "really" speaker-independent or speaker-invariant features, called speech structure, is explained. Speaker variation can be modeled as feature space transformation and our speech structure model is based on the transform-invariance of f-divergence. This proposal was inspired by findings in classical studies of structural phonology and recent studies of developmental psychology. In this talk, we show how we technically implemented findings obtained in phonology and psychology and we also show some examples of applying speech structure to speech applications.

Nobuaki Minematsu received the doctor of Engineering in 1995 from the University of Tokyo. Currently, he is a full professor there. He has a wide interest in speech communication covering from science to engineering. He has published more than 400 scientific and technical papers including conference papers, which focus on speech analysis, speech perception, speech disorder, speech recognition, speech synthesis, dialogue system, language learning systems, etc. He received paper awards from RISP, JSAI, ICIST, O-COCOSDA in 2005, 2007, 2011, and 2014 and received an encouragement award from PSJ in 2014. He gave a tutorial talk on CALL at APSIPA2011 and INTERSPEECH2012. Recently, he developed an online tutoring system OJAD (Online Japanese Accent Dictionary) for learners/teachers of Japanese, which has been introduced to many international institutes of Japanese language education. On March 26 and 27, three workshops will be given at Beijing Foreign Studies University, Beijing Language and Culture University, and Beijing Normal University. He is a member of IEEE, ISCA, IPA, SLaTE, IEICE, ASJ, etc.

←上一版本		2015年5月15日 (五) 11:40的版本
第20行：		第20行：


−	[http://www.gavo.t.u-tokyo.ac.jp/~mine/speech_structure2.pdf\|slides]	+	[http://www.gavo.t.u-tokyo.ac.jp/~mine/speech_structure2.pdf slides]

←上一版本		2015年5月15日 (五) 11:39的版本
第18行：		第18行：

	[[文件:20150330 104102.jpg\|300px]]		[[文件:20150330 104102.jpg\|300px]]
		+
		+
		+	[http://www.gavo.t.u-tokyo.ac.jp/~mine/speech_structure2.pdf\|slides]

←上一版本		2015年4月3日 (五) 02:05的版本
第1行：		第1行：
	'''Speech structure; human-inspired representation of speech acoustics'''		'''Speech structure; human-inspired representation of speech acoustics'''
		+
	— What are "really" speaker-independent features? —		— What are "really" speaker-independent features? —

@@ 第1行： / 第1行： @@
-*Time: 2015/03/30 10AM
+'''Speech structure; human-inspired representation of speech acoustics'''
-*Venue: FIT BLDG, 1-315
+— What are "really" speaker-independent features? —
 Speech signals covey various kinds of information, which are broadly grouped into two kinds, linguistic and extra-linguistic information. Many speech applications, however, focus on only a single aspect of speech. For example, speech recognizers try to extract only word identity from speech signals and speaker recognizers extract only speaker identity. Here, irrelevant aspects are often treated as hidden or latent by applying the probability theory to a large number of samples or the irrelevant aspects are normalized to have quasi-standard values. In speech analysis, however, phases are usually removed, not hidden or normalized, and pitch harmonics are also removed, not hidden or normalized. The resulting speech spectrum still contains both linguistic (word identity) and extra‐linguistic information (speaker identity). Is there any good method to remove extra-linguistic information from the spectrum? In this talk, our proposal of "really" speaker-independent or speaker-invariant features, called speech structure, is explained. Speaker variation can be modeled as feature space transformation and our speech structure model is based on the transform-invariance of f-divergence. This proposal was inspired by findings in classical studies of structural phonology and recent studies of developmental psychology. In this talk, we show how we technically implemented findings obtained in phonology and psychology and we also show some examples of applying speech structure to speech applications.

←上一版本		2015年4月3日 (五) 02:04的版本
第14行：		第14行：


−	[[文件:20150330 104622.jpg]]	+	[[文件:20150330 104622.jpg\|300px]]

−	[[文件:20150330 104102.jpg]]	+	[[文件:20150330 104102.jpg\|300px]]

←上一版本		2015年4月3日 (五) 02:03的版本
第15行：		第15行：

	[[文件:20150330 104622.jpg]]		[[文件:20150330 104622.jpg]]
		+
		+	[[文件:20150330 104102.jpg]]

←上一版本		2015年4月3日 (五) 02:02的版本
第11行：		第11行：

	Nobuaki Minematsu received the doctor of Engineering in 1995 from the University of Tokyo. Currently, he is a full professor there. He has a wide interest in speech communication covering from science to engineering. He has published more than 400 scientific and technical papers including conference papers, which focus on speech analysis, speech perception, speech disorder, speech recognition, speech synthesis, dialogue system, language learning systems, etc. He received paper awards from RISP, JSAI, ICIST, O-COCOSDA in 2005, 2007, 2011, and 2014 and received an encouragement award from PSJ in 2014. He gave a tutorial talk on CALL at APSIPA2011 and INTERSPEECH2012. Recently, he developed an online tutoring system OJAD (Online Japanese Accent Dictionary) for learners/teachers of Japanese, which has been introduced to many international institutes of Japanese language education. On March 26 and 27, three workshops will be given at Beijing Foreign Studies University, Beijing Language and Culture University, and Beijing Normal University. He is a member of IEEE, ISCA, IPA, SLaTE, IEICE, ASJ, etc.		Nobuaki Minematsu received the doctor of Engineering in 1995 from the University of Tokyo. Currently, he is a full professor there. He has a wide interest in speech communication covering from science to engineering. He has published more than 400 scientific and technical papers including conference papers, which focus on speech analysis, speech perception, speech disorder, speech recognition, speech synthesis, dialogue system, language learning systems, etc. He received paper awards from RISP, JSAI, ICIST, O-COCOSDA in 2005, 2007, 2011, and 2014 and received an encouragement award from PSJ in 2014. He gave a tutorial talk on CALL at APSIPA2011 and INTERSPEECH2012. Recently, he developed an online tutoring system OJAD (Online Japanese Accent Dictionary) for learners/teachers of Japanese, which has been introduced to many international institutes of Japanese language education. On March 26 and 27, three workshops will be given at Beijing Foreign Studies University, Beijing Language and Culture University, and Beijing Normal University. He is a member of IEEE, ISCA, IPA, SLaTE, IEICE, ASJ, etc.
		+
		+
		+
		+	[[媒体文件:20150330 104622.jpg]]