检索结果-内蒙古大学图书馆

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Puyang Xu Damianos Karakos Sanjeev Khudanpur Department of Electrical and Computer Engineering Center for Language and Speech Processing USA Human Language Technology Center of Excellence Johns Hopkins University Baltimore MD USA Johns Hopkins University Baltimore MD US

ISBN: (纸本)9781424454785

A novel self-supervised discriminative training method for estimating language models for automatic speech recognition (ASR) is proposed. Unlike traditional discriminative training methods that require transcribed speech, only untranscribed speech and a large text corpus is required. An exponential form is assumed for the language model, as done in maximum entropy estimation, but the model is trained from the text using a discriminative criterion that targets word confusions actually witnessed in first-pass ASR output lattices. Specifically, model parameters are estimated to maximize the likelihood ratio between words w in the text corpus and w's cohorts in the test speech, i.e. other words that w competes with in the test lattices. Empirical results are presented to demonstrate statistically significant improvements over a 4-gram language model on a large vocabulary ASR task.

关键词： Automatic speech recognition Natural languages Lattices Maximum likelihood estimation Humans Testing speech recognition speech processing Entropy Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

A multistage approach for blind separation of convolutive speech mixtures

A multistage approach for blind separation of convolutive sp...

引用

International Conference on Acoustics, speech, and Signal processing (ICASSP)

作者： Tariqullah Jan Wenwu Wang DeLiang Wang Center of Vision Speech and Signal Processing University of Surrey UK Department of Computer Science and Engineering & Center of Cognitive Science Ohio State Uinversity Columbus USA

In this paper, we propose a novel algorithm for the separation of convolutive speech mixtures using two-microphone recordings, based on the combination of independent component analysis (ICA) and ideal binary mask (IBM), together with a post-filtering process in the cepstral domain. Essentially, the proposed algorithm consists of three steps. First, a constrained convolutive ICA algorithm is applied to separate the source signals from two-microphone recordings. In the second step, we estimate the IBM by comparing the energy of corresponding time-frequency (T-F) units from the separated sources obtained with the convolutive ICA algorithm. The last step is to reduce musical noise caused typically by T-F masking using cepstral smoothing. The performance of the proposed approach is evaluated based on both reverberant mixtures generated using a simulated room model and real recordings. The proposed algorithm offers considerably higher efficiency, together with improved speech quality while producing similar separation performance as compared with a recent approach.

关键词： Independent component analysis Signal processing algorithms speech analysis Cepstral analysis Smoothing methods speech processing speech coding Mathematical model Acoustic noise Interference

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of n-gram fast match for query-by-humming systems

Effectiveness of n-gram fast match for query-by-humming syst...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jue Hou Dan-ning Jiang Wen-xiao Cao Yong Qin Thomas Fang Zheng Yi Liu Center of Speech and Language Technologies Division of Technology Innovation and Development Tsinghua National Laboratory of Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China IBM China Research Laboratory Beijing China

To achieve a good balance between matching accuracy and computation efficiency is a key challenge for query-by-humming (QBH) system. In this paper, we propose an approach of n-gram based fast match. Our n-gram method uses a robust statistical note transcription as well as error compensation method based on the analysis of frequent transcription errors. The effectiveness of our approach has been evaluated on a relatively large melody database with 5223 melodies. The experimental results show that when the searching space was reduced to only 10% of the whole size, 90% of the target melodies were preserved in the candidates, and 88% of the match accuracy of system was kept. Meanwhile, no obvious additional computation was applied.

关键词： Databases Computational efficiency Degradation Robustness speech Natural languages Technological innovation Laboratories Information science computer science

来源：评论

学校读者我要写书评

暂无评论

A phrase-level piecewise linear scaling algorithm for melody match in Query-by-Humming systems

A phrase-level piecewise linear scaling algorithm for melody...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wenxiao Cao Danning Jiang Jue Hou Yong Qin Thomas Fang Zheng Yi Liu Center of Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory of Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China IBM China Research Laboratory Beijing China

The Query-by-Humming (QBH) system allows users to retrieve songs by singing/humming. In this paper we propose a phrase-level piecewise linear scaling algorithm for melody match. Musical phrase boundaries are predicted for the query to split it to phrases. The boundaries of melody fragment corresponding to each phrase are allowed for adjusting in a limited scope. The algorithm employs Dynamic Programming and Recursive Alignment to search for the minimal piecewise matching cost upon Linear Scaling at phrase-level. Our experimental results on 5223 melody database show that the proposed algorithm outperforms traditional algorithms. The proposed algorithm gives significant improvements of 17.0%, 14.7% and 4.8% with respect to Linear Scaling, Dynamic Time Wrapping and Recursive Alignment in top-1 rate, respectively. The results show that the proposed algorithm is more efficient than the previous algorithms.

关键词： Piecewise linear techniques Rhythm Natural languages Dynamic programming Costs Heuristic algorithms Databases speech Technological innovation Laboratories

来源：评论

学校读者我要写书评

暂无评论

Recent development of the HMM-based speech synthesis system (HTS)

Recent development of the HMM-based speech synthesis system ...

引用

Asia-Pacific Signal and Information processing Association 2009 Annual Summit and Conference, APSIPA ASC 2009

作者： Zen, Heiga Oura, Keiichiro Nose, Takashi Yamagishi, Junichi Sako, Shinji Toda, Tomoki Masuko, Takashi Black, Alan W. Tokuda, Keiichi Department of Computer Science Nagoya Institute of Technology Nagoya 466-8555 Japan Department of Information Processing Interdisciplinary Tokyo Institute of Technology Yokohama 226-8502 Japan Centre for Speech Technology Research University of Edinburgh Edinburgh EH8-9LW United Kingdom Graduate School of Information Science Nara Institute of Science and Technology Ikoma 630-0192 Japan Language Technologies Institute Carnegie Mellon University Pittsburgh PA 15213 United States Cambridge Research Laboratory Toshiba Research Europe Limited Cambridge CB4 0GZ United Kingdom Corporate Research and Development Center Toshiba Corporation Kawasaki 212-8582 Japan

A statistical parametric approach to speech synthesis based HMMs has grown in popularity over the last few years. In this approach, spectrum, excitation, and duration of speech are simultaneously modeled by context-dependent HMMs, and speech waveforms are generated from the HMMs themselves. Since December 2002, we have publicly released an opensource software toolkit named "HMM-based speech synthesis system (HTS)" to provide a research and development toolkit for statistical parametric speech synthesis. This paper describes recent developments of HTS in detail, as well as future release plans.

关键词： speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Cartoon Motion Capturing and Retargeting by Rigid Shape Manipulation

Cartoon Motion Capturing and Retargeting by Rigid Shape Mani...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Mohammad Rastegari Mohammad Rouhani Niloofar Gheissari Mir Mohsen Pedram Institute of Research in Fundamental Science (IPM) Science & Research Branch Islamic Azad University Tehran Iran Center of Vision Speech and Signal Processing (CVSSP) University of Surrey Guildford Surrey UK Computer Vision Center (cVc) Universitat Authnòma de Barcelona Barcelona Spain Department of Computer Engineering Tarbiat Modares University Tehran Iran

Motion capture from live performance has received a lot of attention in the past few years. However, little work has been done on capturing the motions from existing cartoons. This paper presents a novel approach for capturing motion from existing cartoons and retargeting it to new characters in order to animate them. Most current approaches rely on the identification of key shapes and they fail to directly handle articulated shapes or local deformations. In contrast, we propose to use key-points as more efficient descriptors of motion. We use shape context to capture the motion between successive source frames. Then for retargeting the captured motion to a new character, we use an efficient rigid shape manipulation method that handles local deformations. The proposed method relies on user interaction only for the first source frame. Our algorithm has been applied to a set of test cases and the results shows improved performance in preserving the target's visual style particularly for articulated objects.

关键词： Shape computer vision Interpolation Facial animation Digital images computer applications Application software speech processing Digital signal processing Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Pinyin-indexed method for approximate matching in Chinese

引用

Qinghua Daxue Xuebao/Journal of Tsinghua University 2009年第SUPPL. 1期49卷 1328-1332页

作者： Cao, Jiang Wu, Xiaojun Xia, Yunqing Zheng, Fang Department of Computer Science and Technology Tsinghua University Beijing 100084 China Center for Speech and Language Technologies Division of Technical Innovation and Development Tsinghua National Laboratory for Information Science and Technology Beijing 100084 China

The exact matching of keywords is key to popular commercial search engines. A Chinese approximate matching method with an index structure was developed to achieve better retrieval when the input contains errors. Three types of similarity measurement between two Chinese strings were developed based on the character edit-distance, the Pinyin edit-distance and the Pinyin improved edit-distance. The similarity measurements were used to expand the user's query so that the approximate matching task can be represented as several exact matching sub-tasks. The results of these exact matchings are merged and sorted by their similarity to the original query. Tests on a webpage text database gave a 50.4% recall rate with the Pinyin improved edit-distance with a 60.4% precision with a small increase in time and space complexity.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

A scalable decoder for parsing-based machine translation with equivalent language model state maintenance 2

A scalable decoder for parsing-based machine translation wit...

引用

2nd Workshop on Syntax and Structure in Statistical Translation, SSST 2008

作者： Li, Zhifei Khudanpur, Sanjeev Department of Computer Science and Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States

ISBN: (纸本)9781932432169

We describe a scalable decoder for parsing-based machine translation. The decoder is written in JAVA and implements all the essential algorithms described in Chiang (2007): chart-parsing, m-gram language model integration, beam- and cube-pruning, and unique k-best extraction. Additionally, parallel and distributed computing techniques are exploited to make it scalable. We also propose an algorithm to maintain equivalent language model states that exploits the back-off property of m-gram language models: instead of maintaining a separate state for each distinguished sequence of "state" words, we merge multiple states that can be made equivalent for language model probability calculations due to back-off. We demonstrate experimentally that our decoder is more than 30 times faster than a baseline decoder written in PYTHON. We propose to release our decoder as an open-source toolkit. © 2008 Association for Computational Linguistics

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Translating Compounds by Learning Component Gloss Translation Models via Multiple languages 3

Translating Compounds by Learning Component Gloss Translatio...

引用

3rd International Joint Conference on Natural language processing, IJCNLP 2008

作者： Garera, Nikesh Yarowsky, David Department of Computer Science Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States

This paper presents an approach to the translation of compound words without the need for bilingual training text, by modeling the mapping of literal component word glosses (e.g. "iron-path") into fluent English (e.g. "railway") across multiple languages. Performance is improved by adding component-sequence and learnedmorphology models along with context similarity from monolingual text and optional combination with traditional bilingual-textbased translation discovery. © 2008 IJCNLP 2008 - 3rd International Joint Conference on Natural language processing, Proceedings of the Conference. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Unsupervised translation induction for chinese abbreviations using monolingual corpora

Unsupervised translation induction for chinese abbreviations...

引用

46th Annual Meeting of the Association for Computational Linguistics: Human language Technologies, ACL-08: HLT

作者： Li, Zhifei Yarowsky, David Department of Computer Science Center for Language and Speech Processing Johns Hopkins University Baltimore MD 21218 United States

ISBN: (纸本)9781932432046

Chinese abbreviations are widely used in modern Chinese texts. Compared with English abbreviations (which are mostly acronyms and truncations), the formation of Chinese abbreviations is much more complex. Due to the richness of Chinese abbreviations, many of them may not appear in available parallel corpora, in which case current machine translation systems simply treat them as unknown words and leave them untranslated. In this paper, we present a novel unsupervised method that automatically extracts the relation between a full-form phrase and its abbreviation from monolingual corpora, and induces translation entries for the abbreviation by using its full-form as a bridge. Our method does not require any additional annotated data other than the data that a regular translation system uses. We integrate our method into a state-ofthe- art baseline translation system and show that it consistently improves the performance of the baseline system on various NIST MT test sets. © 2008 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：