AP17:OLR-special session - 版本历史

2017年6月20日 (二) 12:23 Cslt

2017-06-20T12:23:54Z

2017年6月20日 (二) 12:21 Cslt

2017-06-20T12:21:15Z

Liguanyu：/* Title: Tibetan speech database construction */

2017-05-12T00:38:26Z

‎Title: Tibetan speech database construction

Cslt：/* Introduction */

2017-05-02T13:15:16Z

‎Introduction

Cslt：/* Title */

2017-05-02T13:13:47Z

‎Title

2017年5月2日 (二) 13:12 Cslt

2017-05-02T13:12:24Z

Mijiti：/* Potential Papers */

2017-05-02T11:20:40Z

‎Potential Papers

Mijiti：/* Organizers */

2017-05-02T10:43:25Z

‎Organizers

Cslt：/* Potential Papers */

2017-05-02T08:16:12Z

‎Potential Papers

Cslt：/* Organizers */

2017-05-02T08:14:12Z

‎Organizers

@@ 第59行： / 第59行： @@
 ===Title: Language Resource Construction for Mongolian===
-*Author: Shipeng Xu1 , Hongzhi Yu1, Thomas Fang Zheng2 and Jinghao Yan
+*Author: Shipeng Xu , Hongzhi Yu, Thomas Fang Zheng and Jinghao Yan
 *Abstract: Mongolia is a typical low-resource language. The resource limitation is in various aspects, from acoustic
@@ 第66行： / 第66行： @@
 ===Title: Free Linguistic and Speech Resources for Tibetan===
-*Author: Guanyu Li, Hongzhi Yu, Jinghao Yan
+*Author: Guanyu Li, Hongzhi Yu,Thomas Fang Zheng,  Jinghao Yan
 *Abstract: Tibetan is an important low-resource language in China.  A key factor that hinders the speech and language research for Tibetan is the lack of resources, particularly free ones. This paper describes our recent progression on Tibetan resource construction supported by the NSFC M2ASR project, including the phone set, lexicon, as well as the transcription of a large scale speech corpus. Following the M2ASR free data program, all the resources are publicly available and free for researchers. We also release a small Tibetan speech database that can be used to build a proto type Tibetan speech recognition system.

@@ 第39行： / 第39行： @@
-===Title: Prior-constrained multilingual speech recognition ===
+===Title: AP17-OLR Challenge: Data, Plan, and Baseline ===
-*Author: Ying Shi, Zhiyuan Tang, Dong Wang
+*Author: Zhiyuan Tang, Dong Wang, Yixiang Chen, Qing Chen
-*Abstract: Conventional multilingual speech recognition follows ether a tandem approach (language identification)
+*Abstract: We present the data profile and the evaluation plan of the second oriental language recognition (OLR) challenge AP17-OLR.
-or parallel architecture (parallel decoding). This paper presented a novel prior-constrained approach that
+Compare to the event last year (AP16-OLR), the new challenge involves more languages and focuses more on
-conduct the decoding in a multilingual linguistic space, where a prior of the language is used to constrain
+short utterances. The data are
-the decoding frame by frame. Our experiments found that this approach can realize true simultaneous multilingual
+offered by SpeechOcean and the NSFC M2ASR project. Two types of baselines were constructed to assist the participants,
-speech recognition.
+one is based on the i-vector model and the other is based on various neural networks.
-===Title: Memory-based Uyghur-Chinese Translation===
+===Title: Memory-augmented Chinese-Uyghur Neural Machine Translation===
-*Author: Shiyue Zhang, Guli, Mijit Ablimit, Askar Hamdulla
+*Author: Shiyue Zhang, Gulnigar Mahmut, Dong Wang, Askar Hamdulla
-*Abstract: Neural machine translation (NMT) has achieved significant performance. However, this NMT approach
+*Abstract: Neural machine translation (NMT) has achieved notable performance recently. However, this approach has not been widely applied to the translation task between Chinese and Uyghur, partly due to the limited parallel data resource and the large proportion of rare words caused by the agglutinative nature of Uyghur. In this paper, we collect ~200,000 sentence pairs and show that with this middle-scale database, an attention-based NMT can perform very well on Chinese-Uyghur/Uyghur-Chinese translation. To tackle rare words, we propose a novel memory structure to assist the NMT inference. Our experiments demonstrated that the memory-augmented NMT (M-NMT) outperforms both the vanilla NMT and the phrase-based statistical machine translation (SMT).  Interestingly, the memory structure provides an elegant way for dealing with words that are out of vocabulary.
-has not yet effectively applied to minor languages such as Uyghur to Chinese translation. The main problem here
-is that the limited training data does not support an end-to-end neural learning. In this paper, we propose to
-use a memory structure to assist the NMT inference under the condition of limited resource languages. Our experiments
-demonstrated that the this approach is highly efficient compared to the vanilla NMT, and outperforms the conventional
-statistical machine translation (SMT) approach.
-===Title: Resource construction for Mongolia ===
-*Author: Shipeng Xu, Guanyu Li, Hongzhi Yu
+===Title: Language Resource Construction for Mongolian===
 *Abstract: Mongolia is a typical low-resource language. The resource limitation is in various aspects, from acoustic
@@ 第66行： / 第65行： @@
 resource construction supported by the NSFC project.
-===Title: Tibetan speech database construction===
+===Title: Free Linguistic and Speech Resources for Tibetan===
 *Author: Guanyu Li, Hongzhi Yu, Jinghao Yan
-*Abstract: Tibetan is an important low-resource language in China. The syllable structure of Tibetan is similar
+*Abstract: Tibetan is an important low-resource language in China.  A key factor that hinders the speech and language research for Tibetan is the lack of resources, particularly free ones. This paper describes our recent progression on Tibetan resource construction supported by the NSFC M2ASR project, including the phone set, lexicon, as well as the transcription of a large scale speech corpus. Following the M2ASR free data program, all the resources are publicly available and free for researchers. We also release a small Tibetan speech database that can be used to build a proto type Tibetan speech recognition system.
-as Chinese, but the composition rules in orthographic forms is highly complex. Additionally, the lexicon
-resource is far from standard and rich. This paper describes our recent progression on Tibetan
-resource construction supported by the NSFC M2ASR project.
+===Title: A Free Kazak Speech Database and a Speech Recognition Baseline===
-===Title: A large Kazak speech database and a speech recognition baseline===
+*Abstract: Automatic speech recognition (ASR) has gained significant improvement for major languages such as English and Chinese,
-*Author: Askar Hamdulla, Ying Shi
+partly due to the emergence of deep neural networks (DNN) and large amount of training data. For minority languages,
-*Abstract: We describe the construction process of a large scale Kazak speech database. The database involves
+In this paper, we publish a speech database in Kazak, a major minority language in the western China. Accompanying this
-hours of speech signals, recorded by more than 200 speakers. A speech recognition baseline
+database, a full set of phonetic and linguistic resources are also published, by which a full-fledged Kazakh ASR system can be constructed.
-===Title: Multilingual resource construction for Uyghur, Kazak, Kirghiz languages ===
+===Title: A Multilingual Language Processing Tool for Uyghur, Kazak and Kirghiz ===
-*Author: Mijit Ablimit, Askar Hamdulla, Ying Shi,  Dong Wang
+*Author: Mijit Ablimit, Sardar Parhat, Askar Hamdulla, Thomas Fang Zheng
-*Abstract: Minority languages, especially spoken languages, are strongly influenced by major languages or mixing each other. So a platform of uniform phonetic and morphological processing methods can provide a methodology and extra resource for the less popular languages. This paper describes multi-language phonetic and morphological tools and corpus compilation processing for some resource scares languages.
+*Abstract: Natural language processing for less popular languages is difficult, partly due to the high variations in the writing form. On the other hand, many minority languages in the same region share similar properties and can be processed in a similar way. This paper publishes an integrated multilingual language processing tool. Our aim is to provide an open, free and standard toolkit for minority language processing tasks, by a uniform user interface to support multiple languages. The present implementation supports Uyghur, Kazak, Kirghiz, three major minority languages in the Western China, and our focus was put on phonetic and morphological analysis. For the phonetic analysis, we build a multilingual parallel phoneme list, with similar phonemes grouped and character codes standardized. A multilingual syllable analyzer is also developed to detect spelling mistakes, and extract irregular spelling. For the morphological analysis, we build a multilingual morpheme segmentation tool that can extract morphemes by statistical analysis. This toolkit is extendable in terms of both functions and languages.

@@ 第67行： / 第67行： @@
 ===Title: Tibetan speech database construction===
-*Author: Guanyu Li, Hongzhi Yu
+*Author: Guanyu Li, Hongzhi Yu, Jinghao Yan
 *Abstract: Tibetan is an important low-resource language in China. The syllable structure of Tibetan is similar
 as Chinese, but the composition rules in orthographic forms is highly complex. Additionally, the lexicon
 resource is far from standard and rich. This paper describes our recent progression on Tibetan
 resource construction supported by the NSFC M2ASR project.
 ===Title: A large Kazak speech database and a speech recognition baseline===

@@ 第25行： / 第25行： @@
-Minor- and multilingual phenomenon is a important for modern international societies.
+Minor- and multi-lingual phenomenon is a important for modern international societies.
-This special session focuses on minor- and multilingual speech and language processing,
+This special session focuses on minor- and multi-lingual speech and language processing,
 including but not limited to the following topics:
-* Minor- and Multilingual phonetic and phonological analysis
+* Minor- and Multi-lingual phonetic and phonological analysis
-* Minor- and Multilingual speech recognition
+* Minor- and Multi-lingual speech recognition
-* Minor- and Multilingual speaker recognition
+* Minor- and Multi-lingual speaker recognition
-* Minor- and Multilingual speech synthesis
+* Minor- and Multi-lingual speech synthesis
-* Minor- and Multilingual language understanding
+* Minor- and Multi-lingual language understanding
-* Resource construction for minor- and multilingual langauges
+* Resource construction for minority languages
-−
 ==Potential Papers==

@@ 第1行： / 第1行： @@
 ==Title==
-Minor- and Multilingual speech and language processing
+Multilingual speech and language processing for minority languages
 ==Organizers==

@@ 第16行： / 第16行： @@
 '''Mijit Ablimit: Xinjiang University (mijit@xju.edu.cn)
-Dr. Mijit Ablimit got his PhD degree at Kyoto University of Japan. He is now an assiciate professor at the Information Technology and Engineering college of Xinjiang University. His research interest covers speech, language, and multilinuage information processing for less popular languages of China.
+Dr. Mijit Ablimit got his PhD degree at Kyoto University of Japan. He is now an associate professor at the Information Technology and Engineering college of Xinjiang University. His research interest covers speech, language, and multilinuage information processing for less popular languages of China.
 ==Target track==

←上一版本		2017年5月2日 (二) 11:20的版本
第80行：		第80行：
	*Abstract: We describe the construction process of a large scale Kazak speech database. The database involves		*Abstract: We describe the construction process of a large scale Kazak speech database. The database involves
	150 hours of speech signals, recorded by more than 200 speakers. A speech recognition baseline		150 hours of speech signals, recorded by more than 200 speakers. A speech recognition baseline
		+
		+
		+	===Title: Multilingual resource construction for Uyghur, Kazak, Kirghiz languages ===
		+	*Author: Mijit Ablimit, Askar Hamdulla, Ying Shi, Dong Wang
		+	*Abstract: Minority languages, especially spoken languages, are strongly influenced by major languages or mixing each other. So a platform of uniform phonetic and morphological processing methods can provide a methodology and extra resource for the less popular languages. This paper describes multi-language phonetic and morphological tools and corpus compilation processing for some resource scares languages.

←上一版本		2017年5月2日 (二) 10:43的版本
第15行：		第15行：


−	Mijit Ablimit: Xinjiang University (mijit@xju.edu.cn)	+	'''Mijit Ablimit: Xinjiang University (mijit@xju.edu.cn)
		+	Dr. Mijit Ablimit got his PhD degree at Kyoto University of Japan. He is now an assiciate professor at the Information Technology and Engineering college of Xinjiang University. His research interest covers speech, language, and multilinuage information processing for less popular languages of China.

	==Target track==		==Target track==

←上一版本		2017年5月2日 (二) 08:14的版本
第12行：		第12行：
	'''Guanyu Li: Northwest National University (guanyu-li@163.com)'''		'''Guanyu Li: Northwest National University (guanyu-li@163.com)'''

−	Dr. Guanyu Li got his PhD degree at the Northwest University for Nationalities, Gansu Province, China. He worked in several ERP software development companies as a developmental engineer, and is now an associate professor at the Northwest University for Nationalities and the Key Laboratory of National Language Intelligent Processing，Gansu　Province. His research interest includes ~~minor-language~~ speech processing in China, especially speech recognition and speech synthesis. In recent years, he published more than ten papers in related areas.	+	Dr. Guanyu Li got his PhD degree at the Northwest University for Nationalities, Gansu Province, China. He worked in several ERP software development companies as a developmental engineer, and is now an associate professor at the Northwest University for Nationalities and the Key Laboratory of National Language Intelligent Processing，Gansu　Province. His research interest includes speech processing for minor languages in China, especially speech recognition and speech synthesis. In recent years, he published more than ten papers in related areas.