搜索结果: 1-15 共查到“知识库 中国语言文字信息处理”相关记录355条 . 查询时间(5.344 秒)
北京信息科技大学计算机学院文档处理与知识工程团队
北京信息科技大学计算机学院 文档处理与知识工程团队 文档处理 知识工程
2022/12/5
针对交通管理优化和轨迹大数据挖掘的实际应用需求,本文提出了一种支持交通轨迹大数据潜在语义相关性挖掘的交通路网谱聚类方法(TSSC).首先研究了交通轨迹数据的向量空间建模方法,其次通过随机投影法快速提取大规模轨迹数据矩阵的特征信息并构建其低维语义子空间,然后基于语义子空间挖掘轨迹数据的潜在语义相关特性,在此基础上通过谱聚类方法实现了交通路网的快速聚类.通过本文提出的方法对总里程1400多万公里的实际...
深入挖掘微博内容中评价对象与评价词语的词法特征、句法特征、语义特征以及相对位置特征,提出评价对象与评价词语的序列化联合抽取模型.进一步结合微博间转发关系特性提出基于转发关系的联合抽取优化算法.并与相关算法进行实验对比,对实验结果进行了综合分析,证明了方法的可行性和优越性.
针对目前基于字典学习的图像超分辨率重建效果欠佳或字典训练时间过长的问题,本文提出了一种耦合特征空间下改进字典学习的图像超分辨率重建算法.该算法首先利用高斯混合模型聚类算法对训练图像块进行聚类,然后使用更改字典更新方式的改进KSVD字典学习算法来快速获得高、低分辨率特征空间下字典对和映射矩阵.重建时根据测试样本与各个类别的似然概率自适应地选择最匹配的字典对和映射矩阵进行高分辨率重建.最后利用图像非局...
CP-PMTT:一个基于控制流模式的过程模型转换工具
过程模型 模型转换 控制流模式 转换规则
2015/5/20
目前大多数过程模型转换方法采用基于元类映射的转换规则,鉴于因不同过程建模语言在建模符号和语法约束上的差异,而使基于元类映射的转换规则在应对过程模型转换时存在明显局限,提出一种基于控制流模式的过程模型转换框架,转换框架包括一个支持用户自定义控制流模式的控制流模式定义框架,控制流模式定义框架是转换框架的转换核心。通过建立源语言、目标语言和转换核心的映射关系,生成源语言到目标语言的转换规则。基于上述框架...
Unsupervised Spoken Keyword Spotting via Segmental DTW on Gaussian Posteriorgrams
Unsupervised Spoken Keyword Spotting Segmental DTW Gaussian Posterior Grams
2014/11/27
In this paper, we present an unsupervised learning framework to address the problem of detecting spoken keywords. Without any transcription information, a Gaussian Mixture Model is trained to label sp...
Unsupervised Pattern Discovery in Speech
Speech processing unsupervised pattern discovery word acquisition
2014/11/27
We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where the end goal is to cl...
SPEECH RECOGNITION WITH LOCALIZED TIME-FR EQUENCY PATTERN DETECTORS
automatic speech recognition acoustic modeling
2014/11/27
SPEECH RECOGNITION WITH LOCALIZED TIME-FR EQUENCY PATTERN DETECTORS.
Making Sense of Sound: Unsupervised Topic Segmentation over Acoustic Input
Making Sense of Sound Unsupervised Topic Segmentation over Acoustic Input
2014/11/27
We address the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to existing algorithms for topic segmentation of speech, our approach does no...
Exploiting Context Information in Spoken Dialogue Interaction with Mobile Devices
Exploiting Context Information Spoken Dialogue Interaction Mobile Devices
2014/11/27
Today’s mobile phone technology is rapidly evolving towards a personal information assistant model, with the traditional cell phone morphing into a networked mobile device that is capable of managing ...
OPEN-VOCABULARY SPOKEN UTTERANCE RETRIEVAL USING CONFUSION NETWORKS
Spoken Utterance Retrieval Confusion Network Audio Indexing
2014/11/27
This paper presents a novel approach to open-vocabulary spoken utterance retrieval using confusion networks. If out-of-vocabulary (OOV) words are present in queries and the corpus, word-based indexing...
With an average of 17 Chinese characters per phonetic syllable, correcting conversion errors with current phonetic input method editors (IMEs) is often painstaking and time consuming. We explore the a...
UNSUPERVISED WORD ACQUISITION F ROM SPEECH USING PATTERN DISCOVERY
UNSUPERVISED WORD ACQUISITION SPEECH USING PATTERN
2014/11/27
In this paper, we present an unsupervised method for automatically discovering words from speech using a combination of acoustic pattern discovery, graph clustering, and baseform searching. The algori...