Pub Date : 2012-12-02DOI: 10.1109/SLT.2012.6424261
Luiza Orosanu, D. Jouvet, D. Fohr, I. Illina, A. Bonneau
This article analyzes the detection of incorrect entries of non-native speech in the context of foreign language learning. The purpose is to detect and reject incorrect entries (i.e. those for which the speech signal does not correspond at all to the associated text) while being tolerant to the mispronunciations of non-native speech. The proposed approach exploits the comparison between two text-to-speech alignments : one constrained by the text which is being checked, with another one unconstrained, corresponding to a phonetic decoding. Several comparison criteria are described and combined via a logistic regression function. The article analyzes the influence of different settings, such as the impact of non-native pronunciation variants, the impact of learning the decision functions on native or on non-native speech, as well as the impact of combining various comparison criteria. The performance evaluations are conducted both on native and on non-native speech.
{"title":"Combining criteria for the detection of incorrect entries of non-native speech in the context of foreign language learning","authors":"Luiza Orosanu, D. Jouvet, D. Fohr, I. Illina, A. Bonneau","doi":"10.1109/SLT.2012.6424261","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424261","url":null,"abstract":"This article analyzes the detection of incorrect entries of non-native speech in the context of foreign language learning. The purpose is to detect and reject incorrect entries (i.e. those for which the speech signal does not correspond at all to the associated text) while being tolerant to the mispronunciations of non-native speech. The proposed approach exploits the comparison between two text-to-speech alignments : one constrained by the text which is being checked, with another one unconstrained, corresponding to a phonetic decoding. Several comparison criteria are described and combined via a logistic regression function. The article analyzes the influence of different settings, such as the impact of non-native pronunciation variants, the impact of learning the decision functions on native or on non-native speech, as well as the impact of combining various comparison criteria. The performance evaluations are conducted both on native and on non-native speech.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121431058","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424200
William Yang Wang, D. Bohus, Ece Kamar, E. Horvitz
We study the opportunity for using crowdsourcing methods to acquire language corpora for use in natural language processing systems. Specifically, we empirically investigate three methods for eliciting natural language sentences that correspond to a given semantic form. The methods convey frame semantics to crowd workers by means of sentences, scenarios, and list-based descriptions. We discuss various performance measures of the crowdsourcing process, and analyze the semantic correctness, naturalness, and biases of the collected language. We highlight research challenges and directions in applying these methods to acquire corpora for natural language processing applications.
{"title":"Crowdsourcing the acquisition of natural language corpora: Methods and observations","authors":"William Yang Wang, D. Bohus, Ece Kamar, E. Horvitz","doi":"10.1109/SLT.2012.6424200","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424200","url":null,"abstract":"We study the opportunity for using crowdsourcing methods to acquire language corpora for use in natural language processing systems. Specifically, we empirically investigate three methods for eliciting natural language sentences that correspond to a given semantic form. The methods convey frame semantics to crowd workers by means of sentences, scenarios, and list-based descriptions. We discuss various performance measures of the crowdsourcing process, and analyze the semantic correctness, naturalness, and biases of the collected language. We highlight research challenges and directions in applying these methods to acquire corpora for natural language processing applications.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121251118","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424227
Larry Heck, Dilek Z. Hakkani-Tür
This paper proposes an unsupervised training approach for SLU systems that leverages the structured semantic knowledge graphs of the emerging Semantic Web. The approach creates natural language surface forms of entity-relation-entity portions of knowledge graphs using a combination of web search retrieval and syntax-based dependency parsing. The new forms are used to train an SLU system in an unsupervised manner. This paper tests the approach on the problem of intent detection, and shows that the unsupervised training procedure matches the performance of supervised training over operating points important for commercial applications.
{"title":"Exploiting the Semantic Web for unsupervised spoken language understanding","authors":"Larry Heck, Dilek Z. Hakkani-Tür","doi":"10.1109/SLT.2012.6424227","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424227","url":null,"abstract":"This paper proposes an unsupervised training approach for SLU systems that leverages the structured semantic knowledge graphs of the emerging Semantic Web. The approach creates natural language surface forms of entity-relation-entity portions of knowledge graphs using a combination of web search retrieval and syntax-based dependency parsing. The new forms are used to train an SLU system in an unsupervised manner. This paper tests the approach on the problem of intent detection, and shows that the unsupervised training procedure matches the performance of supervised training over operating points important for commercial applications.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125929339","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424263
Sechun Kang, G. G. Lee, Ho-Young Lee, Byeongchang Kim
To improve the English proficiency of Korean learners, we design a system for pitch accents, which consists of prediction, detection and feedback parts. The prediction and detection parts adopt Conditional Random Field models to achieve a prediction accuracy of 87.25%, which is based on the Boston University radio news corpus, and a detection accuracy of 81.21%, which is based on the Korean Learner's English Accentuation corpus. In the learner experiment with our system, learners' pitch accent proficiency, as assessed by English experts, was improved from 2.67 to 3.25 on a scale of 1-to-5, and the accuracy of not-wrong feedback was measured at 82.77%. The learners assessed the learning effectiveness of our system at 4.3 on a scale of 1-to-5.
{"title":"An automatic pitch accent feedback system for english learners with adaptation of an english corpus spoken by Koreans","authors":"Sechun Kang, G. G. Lee, Ho-Young Lee, Byeongchang Kim","doi":"10.1109/SLT.2012.6424263","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424263","url":null,"abstract":"To improve the English proficiency of Korean learners, we design a system for pitch accents, which consists of prediction, detection and feedback parts. The prediction and detection parts adopt Conditional Random Field models to achieve a prediction accuracy of 87.25%, which is based on the Boston University radio news corpus, and a detection accuracy of 81.21%, which is based on the Korean Learner's English Accentuation corpus. In the learner experiment with our system, learners' pitch accent proficiency, as assessed by English experts, was improved from 2.67 to 3.25 on a scale of 1-to-5, and the accuracy of not-wrong feedback was measured at 82.77%. The learners assessed the learning effectiveness of our system at 4.3 on a scale of 1-to-5.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"19 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123280914","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424207
A. Ogawa, Takaaki Hori, Atsushi Nakamura
Techniques for estimating recognition rates without using reference transcriptions are essential if we are to judge whether or not speech recognition technology is applicable to a new task. This paper proposes two recognition rate estimation methods for continuous speech recognition. The first is an easy-to-use method based on a word alignment network (WAN) obtained from a word confusion network through simple conversion procedures. A WAN contains the correct (C), substitution error (S), insertion error (I) and deletion error (D) probabilities word-by-word for a recognition result. By summing these CSID probabilities individually, the percent correct and word accuracy (WACC) can be estimated without using a reference transcription. The second more advanced method refines the CSID probabilities provided by a WAN based on discriminative error type classification (ETC) and estimates the recognition rates more accurately. In the experiments on the MIT lecture speech corpus, we obtained 0.97 of correlation coefficient between the true WACCs calculated by a scoring tool using reference transcriptions and the WACCs estimated from the discriminative ETC results.
{"title":"Recognition rate estimation based on word alignment network and discriminative error type classification","authors":"A. Ogawa, Takaaki Hori, Atsushi Nakamura","doi":"10.1109/SLT.2012.6424207","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424207","url":null,"abstract":"Techniques for estimating recognition rates without using reference transcriptions are essential if we are to judge whether or not speech recognition technology is applicable to a new task. This paper proposes two recognition rate estimation methods for continuous speech recognition. The first is an easy-to-use method based on a word alignment network (WAN) obtained from a word confusion network through simple conversion procedures. A WAN contains the correct (C), substitution error (S), insertion error (I) and deletion error (D) probabilities word-by-word for a recognition result. By summing these CSID probabilities individually, the percent correct and word accuracy (WACC) can be estimated without using a reference transcription. The second more advanced method refines the CSID probabilities provided by a WAN based on discriminative error type classification (ETC) and estimates the recognition rates more accurately. In the experiments on the MIT lecture speech corpus, we obtained 0.97 of correlation coefficient between the true WACCs calculated by a scoring tool using reference transcriptions and the WACCs estimated from the discriminative ETC results.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122714204","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424265
Kyusong Lee, Soo-Ok Kweon, Hongsuck Seo, G. G. Lee
This paper examines how grammar questions are automatically generated for L2 learning by applying a sequential labeling technique to learner corpora. We developed a model that helps detect possible error positions and select the most appropriate form among choices. Discriminant models such as conditional random field and maximum entropy are used to generate the error identification question. Questions generated by the proposed method corresponded highly to questions that experts made. Our data-driven approach lends itself to any language without costing expensive expertise.
{"title":"Generating grammar questions using corpus data in L2 learning","authors":"Kyusong Lee, Soo-Ok Kweon, Hongsuck Seo, G. G. Lee","doi":"10.1109/SLT.2012.6424265","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424265","url":null,"abstract":"This paper examines how grammar questions are automatically generated for L2 learning by applying a sequential labeling technique to learner corpora. We developed a model that helps detect possible error positions and select the most appropriate form among choices. Discriminant models such as conditional random field and maximum entropy are used to generate the error identification question. Questions generated by the proposed method corresponded highly to questions that experts made. Our data-driven approach lends itself to any language without costing expensive expertise.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122923587","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424253
A. Rosenberg
Prosody, or the way words are spoken, carries important information to understanding a speaker's communicative intention. Many studies on automatic prosodic analysis focus on parameterizing pitch content. In this work, we extend previous pitch contour modeling features to intensity contours, and develop a set of features based on the interaction of pitch and intensity. These new features improve the state-of-the-art on all prosodic event detection and classification tasks related to automatic ToBI labeling.
{"title":"Modeling intensity contours and the interaction of pitch and intensity to improve automatic prosodic event detection and classification","authors":"A. Rosenberg","doi":"10.1109/SLT.2012.6424253","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424253","url":null,"abstract":"Prosody, or the way words are spoken, carries important information to understanding a speaker's communicative intention. Many studies on automatic prosodic analysis focus on parameterizing pitch content. In this work, we extend previous pitch contour modeling features to intensity contours, and develop a set of features based on the interaction of pitch and intensity. These new features improve the state-of-the-art on all prosodic event detection and classification tasks related to automatic ToBI labeling.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122078746","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424226
Timothy J. Hazen, Fred Richardson
Latent topic modeling has proven to be an effective means for learning the underlying semantic content within document collections. Latent topic modeling has traditionally been applied to bag-of-words representations that ignore word sequence information that can aid in semantic understanding. In this work we introduce a method for efficiently incorporating arbitrarily long word sequences into a topic modeling approach. This method iteratively constructs a constrained set of phrase trees in an unsupervised fashion from a document collection using weighted pointwise mutual information statistics to guide the process. In experiments on the Fisher Corpus of conversational speech, the incorporation of learned phrases into a latent topic model yielded significant improvements in the unsupervised discovery of the known topics present within the data.
{"title":"Modeling multiword phrases with constrained phrase trees for improved topic modeling of conversational speech","authors":"Timothy J. Hazen, Fred Richardson","doi":"10.1109/SLT.2012.6424226","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424226","url":null,"abstract":"Latent topic modeling has proven to be an effective means for learning the underlying semantic content within document collections. Latent topic modeling has traditionally been applied to bag-of-words representations that ignore word sequence information that can aid in semantic understanding. In this work we introduce a method for efficiently incorporating arbitrarily long word sequences into a topic modeling approach. This method iteratively constructs a constrained set of phrase trees in an unsupervised fashion from a document collection using weighted pointwise mutual information statistics to guide the process. In experiments on the Fisher Corpus of conversational speech, the incorporation of learned phrases into a latent topic model yielded significant improvements in the unsupervised discovery of the known topics present within the data.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116512471","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424160
Teruhisa Misu, H. Kashioka
This paper addresses the problem of feature selection in the reinforcement learning (RL) of the dialog policies of spoken dialog systems. A statistical dialog manager selects the system actions the system should take based on the features derived from the current dialog state and/or the system's belief state. When defining the features used by the system for training the dialog policy, however, finding a set of actually effective features from potentially useful ones is not obvious. In addition, the selection should be done simultaneously with the optimization of the dialog policy. In this paper, we propose an incremental feature selection method for the optimization of a dialog policy by RL, in which improvement of the dialog policy and the feature selection are conducted simultaneously. Experiments in dialog policy optimization by RL with a user simulator demonstrated the following: 1) that the proposed method can find a better dialog policy with fewer policy iterations and 2) the learning speed is comparable with the case where feature selection is conducted in advance.
{"title":"Simultaneous feature selection and parameter optimization for training of dialog policy by reinforcement learning","authors":"Teruhisa Misu, H. Kashioka","doi":"10.1109/SLT.2012.6424160","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424160","url":null,"abstract":"This paper addresses the problem of feature selection in the reinforcement learning (RL) of the dialog policies of spoken dialog systems. A statistical dialog manager selects the system actions the system should take based on the features derived from the current dialog state and/or the system's belief state. When defining the features used by the system for training the dialog policy, however, finding a set of actually effective features from potentially useful ones is not obvious. In addition, the selection should be done simultaneously with the optimization of the dialog policy. In this paper, we propose an incremental feature selection method for the optimization of a dialog policy by RL, in which improvement of the dialog policy and the feature selection are conducted simultaneously. Experiments in dialog policy optimization by RL with a user simulator demonstrated the following: 1) that the proposed method can find a better dialog policy with fewer policy iterations and 2) the learning speed is comparable with the case where feature selection is conducted in advance.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121621114","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}
Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424235
M. Díez, A. Varona, M. Peñagarikano, Luis Javier Rodriguez-Fuentes, Germán Bordel
This paper presents an alternative feature set to the traditional MFCC-SDC used in acoustic approaches to Spoken Language Recognition: the log-likelihood ratios of phone posterior probabilities, hereafter Phone Log-Likelihood Ratios (PLLR), produced by a phone recognizer. In this work, an iVector system trained on this set of features (plus dynamic coefficients) is evaluated and compared to (1) an acoustic iVector system (trained on the MFCC-SDC feature set) and (2) a phonotactic (Phone-lattice-SVM) system, using two different benchmarks: the NIST 2007 and 2009 LRE datasets. iVector systems trained on PLLR features proved to be competitive, reaching or even outperforming the MFCC-SDC-based iVector and the phonotactic systems. The fusion of the proposed approach with the acoustic and phonotactic systems provided even more significant improvements, outperforming state-of-the-art systems on both benchmarks.
{"title":"On the use of phone log-likelihood ratios as features in spoken language recognition","authors":"M. Díez, A. Varona, M. Peñagarikano, Luis Javier Rodriguez-Fuentes, Germán Bordel","doi":"10.1109/SLT.2012.6424235","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424235","url":null,"abstract":"This paper presents an alternative feature set to the traditional MFCC-SDC used in acoustic approaches to Spoken Language Recognition: the log-likelihood ratios of phone posterior probabilities, hereafter Phone Log-Likelihood Ratios (PLLR), produced by a phone recognizer. In this work, an iVector system trained on this set of features (plus dynamic coefficients) is evaluated and compared to (1) an acoustic iVector system (trained on the MFCC-SDC feature set) and (2) a phonotactic (Phone-lattice-SVM) system, using two different benchmarks: the NIST 2007 and 2009 LRE datasets. iVector systems trained on PLLR features proved to be competitive, reaching or even outperforming the MFCC-SDC-based iVector and the phonotactic systems. The fusion of the proposed approach with the acoustic and phonotactic systems provided even more significant improvements, outperforming state-of-the-art systems on both benchmarks.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126215253","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：