2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)最新文献_第8页

Automatic speech recognition based on weighted minimum classification error (W-MCE) training method 基于加权最小分类误差(W-MCE)的自动语音识别训练方法

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430124

Qiang Fu, B. Juang

{"title":"Automatic speech recognition based on weighted minimum classification error (W-MCE) training method","authors":"Qiang Fu, B. Juang","doi":"10.1109/ASRU.2007.4430124","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430124","url":null,"abstract":"The Bayes decision theory is the foundation of the classical statistical pattern recognition approach. For most of pattern recognition problems, the Bayes decision theory is employed assuming that the system performance metric is defined as the simple error counting, which assigns identical cost to each recognition error. However, this prevalent performance metric is not desirable in many practical applications. For example, the cost of \"recognition\" error is required to be differentiated in keyword spotting systems. In this paper, we propose an extended framework for the speech recognition problem with non-uniform classification/recognition error cost. As the system performance metric, the recognition error is weighted based on the task objective. The Bayes decision theory is employed according to this performance metric and the decision rule with a non-uniform error cost function is derived. We argue that the minimum classification error (MCE) method, after appropriate generalization, is the most suitable training algorithm for the \"optimal\" classifier design to minimize the weighted error rate. We formulate the weighted MCE (W-MCE) algorithm based on the conventional MCE infrastructure by integrating the error cost and the recognition error count into one objective function. In the context of automatic speech recognition (ASR), we present a variety of training scenarios and weighting strategies under this extended framework. The experimental demonstration for large vocabulary continuous speech recognition is provided to support the effectiveness of our approach.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129139223","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

Multiple feature combination to improve speaker diarization of telephone conversations 多种功能组合，提高电话通话的说话人拨号化

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430198

Vishwa Gupta, P. Kenny, P. Ouellet, Gilles Boulianne, P. Dumouchel

{"title":"Multiple feature combination to improve speaker diarization of telephone conversations","authors":"Vishwa Gupta, P. Kenny, P. Ouellet, Gilles Boulianne, P. Dumouchel","doi":"10.1109/ASRU.2007.4430198","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430198","url":null,"abstract":"We report results on speaker diarization of telephone conversations. This speaker diarization process is similar to the multistage segmentation and clustering system used in broadcast news. It consists of an initial acoustic change point detection algorithm, iterative Viterbi re-segmentation, gender labeling, agglomerative clustering using a Bayesian information criterion (BIC), followed by agglomerative clustering using state-of-the-art speaker identification methods (SID) and Viterbi re-segmentation using Gaussian mixture models (GMMs). The Viterbi re-segmentation using GMMs is new, and it reduces the diarization error rate (DER) by 10%. We repeat these multistage segmentation and clustering steps twice: once with MFCCs as feature parameters for the GMMs used in gender labeling, SID and Viterbi re-segmentation steps, and another time with Gaussianized MFCCs as feature parameters for the GMMs used in these three steps. The resulting clusters from the parallel runs are combined in a novel way that leads to a significant reduction in the DER. On a development set containing 30 telephone conversations, this combination step reduced the DER by 20%. On another test set containing 30 telephone conversations, this step reduced the DER by 13%. The best error rate we have achieved is 6.7% on the development set, and 9.0% on the test set.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128118989","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: 6

The Titech large vocabulary WFST speech recognition system Titech大词汇量WFST语音识别系统

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430153

Paul R. Dixon, D. Caseiro, T. Oonishi, S. Furui

引用次数: 66

Agglomerative information bottleneck for speaker diarization of meetings data 会议数据的演讲者划分的聚集性信息瓶颈

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430119

Deepu Vijayasenan, F. Valente, H. Bourlard

引用次数: 34

Integrating several annotation layers for statistical information distillation 集成多个注释层，用于统计信息蒸馏

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430192

Michael Levit, Dilek Z. Hakkani-Tür, Gökhan Tür, D. Gillick

{"title":"Integrating several annotation layers for statistical information distillation","authors":"Michael Levit, Dilek Z. Hakkani-Tür, Gökhan Tür, D. Gillick","doi":"10.1109/ASRU.2007.4430192","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430192","url":null,"abstract":"We present a sentence extraction algorithm for Information Distillation, a task where for a given templated query, relevant passages must be extracted from massive audio and textual document sources. For each sentence of the relevant documents (that are assumed to be known from the upstream stages) we employ statistical classification methods to estimate the extent of its relevance to the query, whereby two aspects of relevance are taken into account: the template (type) of the query and its slots (free-text descriptions of names, organizations, topic, events and so on, around which templates are centered). The idiosyncrasy of the presented method is in the choice of features used for classification. We extract our features from charts, compilations of elements from various annotation levels, such as word transcriptions, syntactic and semantic parses, and Information Extraction annotations. In our experiments we show that this integrated approach outperforms a purely lexical baseline by as much as 30% relative in terms of F-measure. We also investigate the algorithm's behavior under noisy conditions, by comparing its performance on ASR output and on corresponding manual transcriptions.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131217485","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

Use of syllable nuclei locations to improve ASR 使用音节核位置来提高ASR

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430134

C. Bartels, J. Bilmes

引用次数: 15

Example-based error recovery strategy for spoken dialog system 基于实例的口语对话系统错误恢复策略

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430169

Cheongjae Lee, Sangkeun Jung, Donghyeon Lee, G. G. Lee

引用次数: 11

A constrained line search approach to general discriminative HMM training 通用判别HMM训练的约束线搜索方法

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430126

Peng Liu, Cong Liu, Hui Jiang, F. Soong, Ren-Hua Wang

引用次数: 7

Exploiting complementary aspects of phonological features in automatic speech recognition 语音自动识别中语音特征的互补利用

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430082

P. MomayyezSiahkal, James Waterhouse, R. Rose

引用次数: 5

Improving lecture speech summarization using rhetorical information 运用修辞信息改进演讲总结

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) Pub Date : 2007-12-01 DOI: 10.1109/ASRU.2007.4430108

J. Zhang, R. Chan, Pascale Fung

{"title":"Improving lecture speech summarization using rhetorical information","authors":"J. Zhang, R. Chan, Pascale Fung","doi":"10.1109/ASRU.2007.4430108","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430108","url":null,"abstract":"We propose a novel method of extractive summarization of lecture speech based on unsupervised learning of its rhetorical structure. We present empirical evidence showing that rhetorical structure is the underlying semantics which is then rendered in linguistic and acoustic/prosodic forms in lecture speech. We present a first thorough investigation of the relative contribution of linguistic versus acoustic features and show that, at least for lecture speech, what is said is more important than how it is said. We base our experiments on conference speeches and corresponding presentation slides as the latter is a faithful description of the rhetorical structure of the former. We find that discourse features from broadcast news are not applicable to lecture speech. By using rhetorical structure information in our summarizer, its performance reaches 67.87% ROUGE-L F-measure at 30% compression, surpassing all previously reported results. The performance is also superior to the 66.47% ROUGE-L F-measure of baseline summarization performance without rhetorical information. We also show that, despite a 29.7% character error rate in speech recognition, extractive summarization performs relatively well, underlining the fact that spontaneity in lecture speech does not affect the central meaning of lecture speech.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121587397","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: 45