发布求助
文献互助 智能选刊 最新文献

2008 IEEE Spoken Language Technology Workshop最新文献

筛选
英文 中文
Efficient sentence segmentation using syntactic features 利用句法特征进行高效的句子切分
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777844
Benoit Favre, Dilek Z. Hakkani-Tür, Slav Petrov, D. Klein
{"title":"Efficient sentence segmentation using syntactic features","authors":"Benoit Favre, Dilek Z. Hakkani-Tür, Slav Petrov, D. Klein","doi":"10.1109/SLT.2008.4777844","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777844","url":null,"abstract":"To enable downstream language processing,automatic speech recognition output must be segmented into its individual sentences. Previous sentence segmentation systems have typically been very local,using low-level prosodic and lexical features to independently decide whether or not to segment at each word boundary position. In this work,we leverage global syntactic information from a syntactic parser, which is better able to capture long distance dependencies. While some previous work has included syntactic features, ours is the first to do so in a tractable, lattice-based way, which is crucial for scaling up to long-sentence contexts. Specifically, an initial hypothesis lattice is constructed using local features. Candidate sentences are then assigned syntactic language model scores. These global syntactic scores are combined with local low-level scores in a log-linear model. The resulting system significantly outperforms the most popular long-span model for sentence segmentation (the hidden event language model) on both reference text and automatic speech recognizer output from news broadcasts.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128902948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 25
Using output probability distribution for oov word rejection 使用输出概率分布进行oov字拒绝
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777880
Shilei Huang, Xiang Xie, Pascale Fung
{"title":"Using output probability distribution for oov word rejection","authors":"Shilei Huang, Xiang Xie, Pascale Fung","doi":"10.1109/SLT.2008.4777880","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777880","url":null,"abstract":"This paper proposes a method to calculate the confidence score for out-of-vocabulary (OOV) word verification based on the Output Probability Distribution (OPD) of phoneme HMMs. Compared with input vector for dynamic garbage model, OPD vector contains more information than the sorted probabilities. Confidence score of each phoneme is calculated by SVM with OPD vectors as input. Hypotheses are accepted or rejected based on this confidence score. Experimental results showed that the proposed method achieved lower EER in word verification task than the conventional dynamic garbage model.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115756977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Hierarchical HMM-based semantic concept labeling model 基于层次hmm的语义概念标注模型
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777839
K. T. Mengistu, M. Hannemann, T. Baum, A. Wendemuth
{"title":"Hierarchical HMM-based semantic concept labeling model","authors":"K. T. Mengistu, M. Hannemann, T. Baum, A. Wendemuth","doi":"10.1109/SLT.2008.4777839","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777839","url":null,"abstract":"An utterance can be conceived as a hidden sequence of semantic concepts expressed in words or phrases. The problem of understanding the meaning underlying a spoken utterance in a dialog system can be partly solved by decoding the hidden sequence of semantic concepts from the observed sequence of words. In this paper, we describe a hierarchical HMM-based semantic concept labeling model trained on semantically unlabeled data. The hierarchical model is compared with a flat concept based model in terms of performance, ambiguity resolution ability and expressive power of the output. It is shown that the proposed method outperforms the flat-concept model in these points.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125952109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Efficient data selection for machine translation 高效的机器翻译数据选择
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777890
Arindam Mandal, D. Vergyri, Wen Wang, Jing Zheng, A. Stolcke, Gökhan Tür, Dilek Z. Hakkani-Tür, N. F. Ayan
{"title":"Efficient data selection for machine translation","authors":"Arindam Mandal, D. Vergyri, Wen Wang, Jing Zheng, A. Stolcke, Gökhan Tür, Dilek Z. Hakkani-Tür, N. F. Ayan","doi":"10.1109/SLT.2008.4777890","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777890","url":null,"abstract":"Performance of statistical machine translation (SMT) systems relies on the availability of a large parallel corpus which is used to estimate translation probabilities. However, the generation of such corpus is a long and expensive process. In this paper, we introduce two methods for efficient selection of training data to be translated by humans. Our methods are motivated by active learning and aim to choose new data that adds maximal information to the currently available data pool. The first method uses a measure of disagreement between multiple SMT systems, whereas the second uses a perplexity criterion. We performed experiments on Chinese-English data in multiple domains and test sets. Our results show that we can select only one-fifth of the additional training data and achieve similar or better translation performance, compared to that of using all available data.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125088890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 27
On-the-fly term spotting by phonetic filtering and request-driven decoding 基于语音过滤和请求驱动解码的动态词汇识别
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777901
Mickael Rouvier, G. Linarès, B. Lecouteux
{"title":"On-the-fly term spotting by phonetic filtering and request-driven decoding","authors":"Mickael Rouvier, G. Linarès, B. Lecouteux","doi":"10.1109/SLT.2008.4777901","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777901","url":null,"abstract":"This paper addresses the problem of on-the-fly term spotting in continuous speech streams. We propose a 2-level architecture in which recall and accuracy are sequentially optimized. The first level uses a cascade of phonetic filters to select the speech segments which probably contain the targeted terms. The second level performs a request-driven decoding of the selected speech segments. The results show good performance of the proposed system on broadcast news data : the best configuration reaches a F-measure of about 94% while respecting the on-the-fly processing constraint.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129897628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Semantic annotations for conversational speech: From speech transcriptions to predicate argument structures 会话语音的语义注释:从语音转录到谓词参数结构
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777841
Arianna Bisazza, Marco Dinarelli, S. Quarteroni, Sara Tonelli, Alessandro Moschitti, G. Riccardi
{"title":"Semantic annotations for conversational speech: From speech transcriptions to predicate argument structures","authors":"Arianna Bisazza, Marco Dinarelli, S. Quarteroni, Sara Tonelli, Alessandro Moschitti, G. Riccardi","doi":"10.1109/SLT.2008.4777841","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777841","url":null,"abstract":"In this paper, we describe the semantic content, which can be automatically generated, for the design of advanced dialog systems. Since the latter will be based on machine learning approaches, we created training data by annotating a corpus with the needed content. Given a sentence of our transcribed corpus, domain concepts and other linguistic levels ranging from basic ones, i.e. part-of-speech tagging and constituent chunking level, to more advanced ones, i.e. syntactic and predicate argument structure (PAS) levels are annotated. In particular, the proposed PAS and taxonomy of dialog acts appear to be promising for the design of more complex dialog systems. Statistics about our semantic annotation are reported.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129558654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Learning the morphology of Zulu with different degrees of supervision 在不同程度的监督下学习祖鲁语的形态
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777827
Sebastian Spiegler, B. Golénia, Kseniya B. Shalonova, Peter A. Flach, R. Tucker
{"title":"Learning the morphology of Zulu with different degrees of supervision","authors":"Sebastian Spiegler, B. Golénia, Kseniya B. Shalonova, Peter A. Flach, R. Tucker","doi":"10.1109/SLT.2008.4777827","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777827","url":null,"abstract":"In this paper we compare different levels of supervision for learning the morphology of the indigenous South African language Zulu. After a preliminary analysis of the Zulu data used for our experiments, we concentrate on supervised, semi-supervised and unsupervised approaches comparing strengths and weaknesses of each method. The challenges we face are limited data availability and data sparsity in connection with morphological analysis of indigenous languages. At the end of the paper we draw conclusions for our future work towards a morphological analyzer for Zulu.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125228576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 19
RSHMM++ for extractive lecture speech summarization rshmm++用于抽取讲座演讲摘要
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777865
J. Zhang, Shilei Huang, Pascale Fung
{"title":"RSHMM++ for extractive lecture speech summarization","authors":"J. Zhang, Shilei Huang, Pascale Fung","doi":"10.1109/SLT.2008.4777865","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777865","url":null,"abstract":"We propose an enhanced Rhetorical-State Hidden Markov Model (RSHMM++) for extracting hierarchical structural summaries from lecture speech. One of the most underutilized information in extractive summarization is rhetorical structure hidden in speech data. RSHMM++ automatically decodes this underlying information in order to provide better summaries. We show that RSHMM++ gives a 72.01% ROUGE-L F-measure, a 9.78% absolute increase in lecture speech summarization performance compared to the baseline system without using rhetorical information. We also propose Relaxed DTW for compiling reference summaries.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133572161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 12
Recent improvements in BBN's English/Iraqi speech-to-speech translation system BBN英语/伊拉克语语音翻译系统的最新改进
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777886
F. Choi, S. Tsakalidis, S. Saleem, C. Kao, R. Meermeier, K. Krstovski, C. Moran, Krishna Subramanian, R. Prasad, P. Natarajan
{"title":"Recent improvements in BBN's English/Iraqi speech-to-speech translation system","authors":"F. Choi, S. Tsakalidis, S. Saleem, C. Kao, R. Meermeier, K. Krstovski, C. Moran, Krishna Subramanian, R. Prasad, P. Natarajan","doi":"10.1109/SLT.2008.4777886","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777886","url":null,"abstract":"We report on recent improvements in our English/Iraqi Arabic speech-to-speech translation system. User interface improvements include a novel parallel approach to user confirmation which makes confirmation cost-free in terms of dialog duration. Automatic speech recognition improvements include the incorporation of state-of-the-art techniques in feature transformation and discriminative training. Machine translation improvements include a novel combination of multiple alignments derived from various pre-processing techniques, such as Arabic segmentation and English word compounding, higher order N-grams for target language model, and use of context in form of semantic classes and part-of-speech tags.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133218748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
Morphological random forests for language modeling of inflectional languages 形态学随机森林用于屈折语言的语言建模
2008 IEEE Spoken Language Technology Workshop Pub Date : 2008-12-01 DOI: 10.1109/SLT.2008.4777872
I. Oparin, O. Glembek, L. Burget, J. Černocký
{"title":"Morphological random forests for language modeling of inflectional languages","authors":"I. Oparin, O. Glembek, L. Burget, J. Černocký","doi":"10.1109/SLT.2008.4777872","DOIUrl":"https://doi.org/10.1109/SLT.2008.4777872","url":null,"abstract":"In this paper, we are concerned with using decision trees (DT) and random forests (RF) in language modeling for Czech LVCSR. We show that the RF approach can be successfully implemented for language modeling of an inflectional language. Performance of word-based and morphological DTs and RFs was evaluated on lecture recognition task. We show that while DTs perform worse than conventional trigram language models (LM), RFs of both kind outperform the latter. WER (up to 3.4% relative) and perplexity (10%) reduction over the trigram model can be gained with morphological RFs. Further improvement is obtained after interpolation of DT and RF LMs with the trigram one (up to 15.6% perplexity and 4.8% WER relative reduction). In this paper we also investigate distribution of morphological feature types chosen for splitting data at different levels of DTs.","PeriodicalId":186876,"journal":{"name":"2008 IEEE Spoken Language Technology Workshop","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121807411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 16
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书