检索结果-南通市图书馆

2011年亚太信号与信息处理协会年会

作者： tatsuya kawahara Kyoto University Kyoto 606-8501 Japan

High non-native speech recognition performance is always a challenge for a CALL （Computer Assisted Language Learning） systems using ASR （Automatic Speech Recognition） for second language learning. Conventionally, possible error patterns, based on linguistic knowledge, are added to the ASR grammar network. However, the effectiveness of this approach depends much on the prior linguistic knowledge. In this paper, we design a new scheme for error prediction using two sequential machine learning methods. The first step of the prediction method is aiming at the generality, in which decision tree-based error prediction is adopted in our previous work. The second step of the training is aiming at removing most of the redundant candidates. For the second step, we propose a method based on discriminative training to judge the error candidates that degrade the ASR performance and remove them from the ASR grammar network. An experimental evaluation shows that the proposed method can effectively improve non-native speech recognition performance by drastically reducing the False Alarm rate. Moreover, the smaller WER （Word Error Rate） also confirms the effectiveness of our method.

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Optimized Wavelet-based Speech Enhancement for Speech Recognition in Noisy and Reverberant Conditions

Optimized Wavelet-based Speech Enhancement for Speech Recogn...

引用

2011年亚太信号与信息处理协会年会

作者： Randy Gomez tatsuya kawahara Kyoto University Academic Center for Computing and Media Studies （ACCMS） Sakyo-ku Kyoto 606-8501 JAPAN

We present an improved speech enhancement method based on Wiener filtering in the wavelet domain for automatic speech recognition （ASR）. The wavelet coefficients that are contaminated by the effects of late reflection and background noise are filtered using a Wiener gain. We optimize the wavelet parameters for speech, background noise and late reflection to achieve a better estimate of the Wiener gain for effective filtering. Wiener gains to compensate for the effects of late reflection and background noise are independently estimated and then combined. Moreover, we introduce the noise profile and reverberation time identification to cope with different noise and reverberant conditions. Experimental results in large vocabulary continuous speech recognition （LVCSR） show that the proposed method outperforms the conventional methods.

关键词： Speech enhancement Speech recognition Noise BACKGROUND NOISE bockwurst Wiener filters Wavelet domain Reflection

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

FREE SOFTWARE TOOLKIT FOR JAPANESE LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

FREE SOFTWARE TOOLKIT FOR JAPANESE LARGE VOCABULARY CONTINUO...

引用

6～(th) International Conference on Spoken Language Processing

作者： tatsuya kawahara Akinobu Lee Tetsunori Kobayashi Kazuya Takeda Nobuaki Minematsu Shigeki Sagayama Katsunobu Itou Akinori Ito Mikio Yamamoto Atsushi Yamada Takehito Utsuro Kiyohiro Shikano School of Informatics. Kyoto University 606-8501. Japan Kyoto Univ Waseda Univ Nagoya Univ Tokyo Univ Tokyo Univ ETL Yamagata Univ Tsukuba Univ ASTEM Toyohashi Univ. Tech Nara Inst. of Sci. ＆ Tech

＜正＞A sharable software repository for Japanese LVCSR （Large Vocabulary Continuous Speech Recognition） is introduced. It is designed as a baseline platform for research and developed by researchers of different academic institutes under a governmental support. The repository consists of a recognition engine （Julius）, Japanese acoustic models and statistical language models us well as Japanese morphological analysis tools. These modules can be easily integrated and replaced under a plug-and-play framework, which makes it possible to fairly evaluate components and to develop specific application systems. Assessment of these modules and systems in a 20000-word dictation task is reported. The software repository is freely available to the public.

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Efficacy and safety of endoscopic submucosal dissection for gastric tube cancer:A multicenter retrospective study

引用

World Journal of Gastroenterology 2021年第11期27卷 1043-1054页

作者： Takuya Satomi Seiji Kawano Tomoki Inaba Masahiro Nakagawa Hirokazu Mouri Masao Yoshioka Shoichi Tanaka tatsuya Toyokawa Sayo Kobayashi Takehiro Tanaka Hiromitsu Kanzaki Masaya Iwamuro Yoshiro kawahara Hiroyuki OkadaDepartment of Gastroenterology and Hepatology Department of Gastroenterology and Hepatology Okayama University Graduate School of MedicineDentistryand Pharmaceutical SciencesOkayama 700-8558OkayamaJapan Department of Gastroenterology Kagawa Prefectural Central HospitalTakamatsu 760-8557KagawaJapan Department of Endoscopy Hiroshima City Hiroshima Citizens HospitalHiroshima 730-8518HiroshimaJapan Department of Gastroenterology and Hepatology Kurashiki Central HospitalKurashiki 710-8602OkayamaJapan Department of Gastroenterology and Hepatology Okayama Saiseikai General HospitalOkayama 700-8511OkayamaJapan Department of Gastroenterology National Hospital Organization Iwakuni Clinical CenterIwakuni 740-8510YamaguchiJapan Department of Gastroenterology National Hospital Organization Fukuyama Medical CenterFukuyama 720-8521HiroshimaJapan Department of Internal Medicine Fukuyama City HospitalFukuyama 721-8511HiroshimaJapan Department of Pathology Okayama University HospitalOkayama 700-8558OkayamaJapan Department of Practical Gastrointestinal Endoscopy Okayama University Graduate School of MedicineDentistry and Pharmaceutical SciencesOkayama 700-8558OkayamaJapan

BACKGROUND Recent improvements in the prognosis of patients with esophageal cancer have led to the increased occurrence of gastric tube cancer(GTC)in the reconstructed gastric ***,there are few reports on the treatment results of endoscopic submucosal dissection(ESD)for *** To evaluate the efficacy and safety of ESD for GTC after esophagectomy in a multicenter *** We retrospectively investigated 48 GTC lesions in 38 consecutive patients with GTC in the reconstructed gastric tube after esophagectomy who had undergone ESD between January 2005 and December 2019 at 8 institutions participating in the Okayama Gut Study *** clinical indications of ESD for early gastric cancer were similarly applied for GTC after *** specimens were evaluated in 2-mm slices according to the Japanese Classification of Gastric Carcinoma with curability assessments divided into curative and non-curative resection based on the Gastric Cancer Treatment *** characteristics,treatment results,clinical course,and treatment outcomes were *** The median age of patients was 71.5 years(range,57-84years),and there were 34 men and 4 *** median observation period after ESD was 884 d(range,8-4040 d).The median procedure time was 81 min(range,29-334 min),the en bloc resection rate was 91.7%(44/48),and the curative resection rate was 79%(38/48).Complications during ESD were seen in 4%(2/48)of case,and those after ESD were seen in 10%(5/48)of *** survival rate at 5 years was 59.5%.During the observation period after ESD,10 patients died of other *** there were differences in the procedure time between institutions,a multivariate analysis showed that tumor size was the only factor associated with prolonged procedure *** ESD for GTC after esophagectomy was shown to be safe and effective.

关键词： Endoscopic submucosal dissection Gastric tube Gastric cancer Esophagectomy Multicenter study Retrospective study

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：