检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

136 篇 会议

馆藏范围

136 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

75 篇 理学
- 75 篇 系统科学
32 篇 工学
- 15 篇 计算机科学与技术...
- 14 篇 软件工程
- 7 篇 机械工程
- 7 篇 信息与通信工程
- 5 篇 控制科学与工程
- 2 篇 仪器科学与技术
- 1 篇 网络空间安全
28 篇 文学
- 25 篇 中国语言文学
- 3 篇 外国语言文学
16 篇 法学
- 10 篇 社会学
- 6 篇 民族学
2 篇 经济学
- 2 篇 应用经济学
2 篇 管理学
- 2 篇 管理科学与工程(可...
2 篇 艺术学
- 2 篇 设计学（可授艺术学...

主题

15 篇 语音识别
4 篇 语种识别
4 篇 计算机辅助语言学...
3 篇 中国科学院自动化...
3 篇 frame
3 篇 ncmmsc2009
3 篇 微软亚洲研究院
3 篇 语音合成
3 篇 语言模型
3 篇 电子工程系
2 篇 说话人确认
2 篇 检索机
2 篇 鲁棒性
2 篇 ncmmsc
2 篇 置信度
2 篇 哼唱识别
2 篇 语音学
2 篇 元音
2 篇 情感识别
2 篇 模糊匹配

机构

19 篇 清华大学
5 篇 西北民族大学
5 篇 中国传媒大学
4 篇 北京交通大学
4 篇 中国社会科学院语...
3 篇 ibm中国研究院
3 篇 哈尔滨工业大学
3 篇 北京理工大学
3 篇 ibm中国研究中心
2 篇 清华信息科学技术...
2 篇 太原理工大学
2 篇 national institu...
2 篇 北京邮电大学
2 篇 清华-讯飞语音技术...
2 篇 北京语言大学
2 篇 中国科学院自动化...
2 篇 graduate school ...
2 篇 北京信息科技大学
2 篇 中国科学技术大学
2 篇 清华大学信息技术...

作者

7 篇 郑方
6 篇 秦勇
5 篇 蔡莲红
5 篇 于洪志
4 篇 邬晓钧
4 篇 李爱军
4 篇 徐明星
3 篇 谢湘
3 篇 苗振江
3 篇 刘轶
3 篇 夏云庆
3 篇 徐波
3 篇 吴及
3 篇 孟子厚
3 篇 双志伟
3 篇 戴礼荣
2 篇 王士进
2 篇 张雪英
2 篇 吐尔洪江·阿布都克...
2 篇 匡镜明

语言

90 篇 中文
46 篇 英文

检索条件"任意字段=第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会"

共 136 条记录，以下是111-120 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Introduction on Several Ethnic Languages Speech Corpus

Introduction on Several Ethnic Languages Speech Corpus

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Yan Liu Minzu University of China

In recent years, the Minzu University of China has established several speech databases of some ethnic languages under the funding of national "211" and "985" programs. These databases include "Speech Corpus of Chinese Endangered Ethnic Languages", "The Interlanguage Corpus of Tibetan Speaking Mandarin Chinese", "Phonetic File of Ethnic Languages in China", and "Multimedia Archive in International Phonetic Alphabet of Ethnic Languages in China" etc. The establishment of these databases is required by the need of protecting intangible culture of ethnic languages in China, developing information technology, promoting Putonghua, language teaching of national languages, and linguistics study, etc. This article will provide basic information on the establishment and study of these databases and the introduction to the supporting platform for construction of language database.

关键词： Introduction on Several Ethnic Languages Speech Corpus

来源：评论

学校读者我要写书评

暂无评论

Eigenvoice-based Approach to Voice Conversion and Voice Quality Control

Eigenvoice-based Approach to Voice Conversion and Voice Qual...

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Tomoki Toda Graduate School of Information Science Nara Institute of Science and Technology (NAIST)Japan

This paper reviews our proposed approach to voice conversion (VC) and voice quality control based on an eigenvoice technique. VC is a technique to modify nonlinguistic information such as speaker individuality while keeping linguistic information unchanged. In the traditional VC framework, a conversion model for a source and target speaker-pair needs to be trained in advance using a parallel data set consisting of utterance-pairs of these two speakers. To make VC technologies more practical, we have developed a new VC paradigm for flexibly building the conversion model for an arbitrary speaker-pair by effectively using speech samples of many other speakers. In this paper, we give an overview of eigenvoice conversion (EVC) as one of our proposed VC techniques.

关键词： GMM frame Eigenvoice-based Approach to Voice Conversion and Voice Quality Control

来源：评论

学校读者我要写书评

暂无评论

MASS:A Malay Language LVCSR Corpus Resource

MASS:A Malay Language LVCSR Corpus Resource

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Tien-Ping Tan USM Malaysian/NTU Singapore

This paper presents the development of the speech, text and pronunciation dictionary resources required to build a large vocabulary speech recognizer for the Malay language. This project is a collaboration project among three universities: USM, MMU from Malaysia and NTU from Singapore. The Malay speech corpus consists of read speech (speaker independent/ dependent and accent independent/ dependent) and broadcast news. To date, 90 speakers have been recorded which is equal to a total of nearly 70 hours of read speech, and 10 hours of broadcast news from local TV stations in Malaysia was transcribed. The text corpus consists of 700Mbytes of data extracted from Malaysia’s local news web pages from 1998-2008 and a rule based G2P tool is develop to generate the pronunciation dictionary.

关键词： MASS:A Malay Language LVCSR Corpus Resource

来源：评论

学校读者我要写书评

暂无评论

Robots that Learn to Converse:Developmental Approach to Situated Language Processing

Robots that Learn to Converse:Developmental Approach to Situ...

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Naoto Iwahashi Ryo Taguchi Komei Sugiura Kotaro Funakoshi Mikio Nakano Nagoya Institute of Technology

This paper presents a machine learning method that enables robots to learn to communicate linguistically from scratch through verbal and behavioral interaction with users. The method combines speech, visual, and tactile information ob- tained by interaction in the real world. It learns speech units, words, concepts of objects, motions, grammar, and pragmatic and communicative capabilities, which are integrated in a dy- namic graphical model. Experimental results show that through a practical, small number of learning episodes with a user, the robot was eventually able to understand even fragmental and ambiguous utterances, respond to them with confirmation ques- tions and/or acting, generate directive utterances appropriate for the given situation, and answer questions. This paper discusses the importance of a developmental approach to realize natural situated human-robot conversations.

关键词： Robots that Learn to Converse:Developmental Approach to Situated Language Processing

来源：评论

学校读者我要写书评

暂无评论

A SPEECH MODIFICATION BASED SINGING VOICE SYNTHESIS SYSTEM

A SPEECH MODIFICATION BASED SINGING VOICE SYNTHESIS SYSTEM

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Jia Jia1, Jun Xu1, Yinjin Xu1, Lianhong Cai1 1.Department of Computer Science and Technology, Tsinghua University, Beijing, China

Singing voice synthesis is one of the hot topics of speech synthesis applications. This paper introduced a speech modification based singing voice synthesis framework and proposed several detailed implementations for improving the quality of synthesized singing voice. Subjective evaluation showed that the proposed methods are effective to enhance the generated singing voice.

关键词： Speech modification, singing voice synthesis, speech-note alignment, TD-PSOLA

来源：评论

学校读者我要写书评

暂无评论

Development and Evaluation of Chinese Conversational Corpora for Speech Recognition in Speech-to-Speech Translation System

Development and Evaluation of Chinese Conversational Corpora...

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Ryosuke Isotani Satoshi Nakamura National Institute of Information and Communications Technology

In this presentation, we describe the development of Chinese conversational segmented and POS-tagged corpora currently used in the NICT speech-to-speech translation system, including design of specifications and methods of annotation work. Over 500K manually checked utterances provide 3.5M words of Chinese corpora. As far as we know, they are the largest conversational textual corpora;in the domain of travel. A set of three parallel corpora is obtained with the corresponding pairs of Japanese and English words from which the Chinese words are translated. Comparative analyses on statistical characteristics of corpora, performances of language models and speech recognitions are conducted using these parallel corpora, and the problems with the Chinese corpora and solutions to them are discussed.

关键词： POS domain Development and Evaluation of Chinese Conversational Corpora for Speech Recognition in Speech-to-Speech Translation System

来源：评论

学校读者我要写书评

暂无评论

Hybrid Method for Spoken Language Translation

Hybrid Method for Spoken Language Translation

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者：王海峰东芝(中国)研究开发中心

Spoken language translation (SLT), which bridges the gap between different languages, plays an important role in speech-to-speech translation. SLT system has to deal with problems such as disfluency, ungrammaticality, absence of punctuation marks, speech recognition errors, etc. Statistical Machine Translation (SMT) is very popular for its adequate mathematical model, unsupervised learning capacity, and robustness. Rule-Based Machine Translation (RBMT) and Example-Based Machine Translation (EBMT) methods are also valuable. Rules are good at modeling linguistic theory and phenomena. EBMT method is able to translate similar input very well. Hybrid machine translation is becoming more and more important in the machine translation community. This report introduces rule-based, example-based and statistical SLT methods and the combination of them.

关键词： Hybrid Method for Spoken Language Translation SLT

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on the Similarity Performance of HMM-based Parametric Speech Synthesis

An Experimental Study on the Similarity Performance of HMM-b...

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Zhen-Hua Ling, Yu Hu (iFLYTEK Research, Hefei, China 230027)

The similarity between the speaker characteristics of synthetic speech and the natural voice of target speaker is an important measurement to evaluate the performance of a speech synthesis system. However, the similarity performance of the HMM-based parametric speech synthesis method is generally unsatisfactory. This paper studies the factors that may cause such similarity degradation by a group of subjective listening tests. These factors include the influence of speech vocoder, the statistical model based generation of duration, F0 and spectral parameters, and rapid voice building by model adaptation. The results show that the generated duration and spectrum parameters are the major reasons that impair the speaker characteristics of synthetic speech. Hence, we experiment by increasing the number of distributions for context-dependent phone duration modeling and introducing unit selection method into spectral parameter generation to improve the similarity performance. The results of listening tests prove that these two means can improve the similarity performance effectively and preserve the naturalness of synthetic speech at the same time.

关键词： Speech synthesis hidden Markov model similarity performance parameter generation

来源：评论

学校读者我要写书评

暂无评论

Japanese children’s perception for audio-visual prosody of social politeness

Japanese children’s perception for audio-visual prosody of ...

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者： Takaaki Shochi Donna Erickson Albert Rilliard Kaoru Sekiyama Véronique Aubergé Division of Cognitive Psychology Kumamoto UniversityJapan Showa Music University Kawasaki City Japan

This paper presents a perception experiment to measure the ability of Japanese children in fourth and fifth grade elementary school to recognize culturally encoded expressions of politeness and impoliteness in their native language. Audio-visual stimuli were presented to listeners, who rate the politeness degree and a possible situation where such an expression could be used. Analysis of results focuses on the differences and the similarities between adult listeners and children, for each attitude and modality. Facial information seems to be retrieved earlier than audio ones, and expressions of different degrees of Japanese politeness, including expressions of kyoshuku, are still not understood around 10 years of age.

关键词： prosodic social affects language acquisition Japanese.

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Multilingual Text-to-Speech Synthesis with SSML Specification as Interface

A Unified Framework for Multilingual Text-to-Speech Synthesi...

引用

第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会

作者：吴志勇曹光琦蒙美玲蔡莲红 Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems Graduate School at ShenzhenTsinghua University

This paper describes the design of a unified framework for a multilingual text-to-speech （TTS） synthesis engine-Crystal. The unified framework defines the common TTS modules for different languages and/or dialects. The interfaces between consecutive modules conform to Speech Synthesis Markup Language （SSML） specification for standardization, interoperability, multilinguality, and extensibility. Detailed module divisions and implementation technologies for the unified framework are introduced, together with possible extension for algorithm research and evaluation of TTS synthesis.

关键词： text-to-speech （TTS） synthesis multilingual unified framework speech synthesis markup language （SSML）

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共14页 << < 5 6 7 8 9 10 11 12 13 14 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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

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：