2014 IEEE Spoken Language Technology Workshop (SLT)最新文献

筛选
英文 中文
Semi-supervised DNN training in meeting recognition 会议识别中的半监督DNN训练
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-08 DOI: 10.1109/SLT.2014.7078564
Pengyuan Zhang, Yulan Liu, Thomas Hain
{"title":"Semi-supervised DNN training in meeting recognition","authors":"Pengyuan Zhang, Yulan Liu, Thomas Hain","doi":"10.1109/SLT.2014.7078564","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078564","url":null,"abstract":"Training acoustic models for ASR requires large amounts of labelled data which is costly to obtain. Hence it is desirable to make use of unlabelled data. While unsupervised training can give gains for standard HMM training, it is more difficult to make use of unlabelled data for discriminative models. This paper explores semi-supervised training of Deep Neural Networks (DNN) in a meeting recognition task. We first analyse the impact of imperfect transcription on the DNN and the ASR performance. As labelling error is the source of the problem, we investigate two options available to reduce that: selecting data with fewer errors, and changing the dependence on noise by reducing label precision. Both confidence based data selection and label resolution change are explored in the context of two scenarios of matched and unmatched unlabelled data. We introduce improved DNN based confidence score estimators and show their performance on data selection for both scenarios. Confidence score based data selection was found to yield up to 14.6% relative WER reduction, while better balance between label resolution and recognition hypothesis accuracy allowed further WER reductions by 16.6% relative in the mismatched scenario.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"29 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128797676","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: 32
But ASR system for BABEL Surprise evaluation 2014 但ASR系统的BABEL惊喜评估2014
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078625
M. Karafiát, Karel Veselý, Igor Szöke, L. Burget, F. Grézl, M. Hannemann, J. Černocký
{"title":"But ASR system for BABEL Surprise evaluation 2014","authors":"M. Karafiát, Karel Veselý, Igor Szöke, L. Burget, F. Grézl, M. Hannemann, J. Černocký","doi":"10.1109/SLT.2014.7078625","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078625","url":null,"abstract":"The paper describes Brno University of Technology (BUT) ASR system for 2014 BABEL Surprise language evaluation (Tamil). While being largely based on our previous work, two original contributions were brought: (1) speaker-adapted bottle-neck neural network (BN) features were investigated as an input to DNN recognizer and semi-supervised training was found effective. (2) Adding of noise to training data outperformed a classical de-noising technique while dealing with noisy test data was found beneficial, and the performance of this approach was verified on a relatively clean training/test data setup from a different language. All results are reported on BABEL 2014 Tamil data.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117144394","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: 11
Annealed dropout training of deep networks 深度网络的退火辍学训练
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078567
Steven J. Rennie, V. Goel, Samuel Thomas
{"title":"Annealed dropout training of deep networks","authors":"Steven J. Rennie, V. Goel, Samuel Thomas","doi":"10.1109/SLT.2014.7078567","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078567","url":null,"abstract":"Recently it has been shown that when training neural networks on a limited amount of data, randomly zeroing, or “dropping out” a fixed percentage of the outputs of a given layer for each training case can improve test set performance significantly. Dropout training discourages the detectors in the network from co-adapting, which limits the capacity of the network and prevents overfitting. In this paper we show that annealing the dropout rate from a high initial value to zero over the course of training can substantially improve the quality of the resulting model. As dropout (approximately) implements model aggregation over an exponential number of networks, this procedure effectively initializes the ensemble of models that will be learned during a given iteration of training with an enemble of models that has a lower average number of neurons per network, and higher variance in the number of neurons per network-which regularizes the structure of the final model toward models that avoid unnecessary co-adaptation between neurons. Importantly, this regularization procedure is stochastic, and so promotes the learning of “balanced” networks with neurons that have high average entropy, and low variance in their entropy, by smoothly transitioning from “exploration” with high learning rates to “fine tuning” with full support for co-adaptation between neurons where necessary. Experimental results demonstrate that annealed dropout leads to significant reductions in word error rate over standard dropout training.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117316845","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: 61
Improving the robustness of example-based dialog retrieval using recursive neural network paraphrase identification 递归神经网络释义识别提高基于实例对话检索的鲁棒性
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078592
Lasguido Nio, S. Sakti, Graham Neubig, T. Toda, Satoshi Nakamura
{"title":"Improving the robustness of example-based dialog retrieval using recursive neural network paraphrase identification","authors":"Lasguido Nio, S. Sakti, Graham Neubig, T. Toda, Satoshi Nakamura","doi":"10.1109/SLT.2014.7078592","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078592","url":null,"abstract":"Previous work on example-based chat-oriented dialog systems utilizing real human-to-human conversation has shown promising results. However, most previous methods use relatively simple retrieval techniques, resulting in weakness to out of vocabulary (OOV) database queries and inadequate handling of interactions between words in the sentence. To overcome this problem, in this paper we propose a method to utilize recursive neural network paraphrase identification to improve the accuracy and robustness of example-based dialog response retrieval. We model our dialog-pair database and user input query with distributed word representations, and employ recursive autoencoders and dynamic pooling to determine whether two sentences with arbitrary length have the same meaning. The distributed representations have the potential to improve handling of OOV cases, and the recursive structure can reduce confusion in example matching. We evaluate the system performance based on objective and subjective metrics.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129064917","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: 7
Machine learning approaches to improving pronunciation error detection on an imbalanced corpus 在不平衡语料库上改进发音错误检测的机器学习方法
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078591
Xuesong Yang, Anastassia Loukina, Keelan Evanini
{"title":"Machine learning approaches to improving pronunciation error detection on an imbalanced corpus","authors":"Xuesong Yang, Anastassia Loukina, Keelan Evanini","doi":"10.1109/SLT.2014.7078591","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078591","url":null,"abstract":"In this paper, we investigate the task of phone-level pronunciation error detection as a binary classification problem, the performance of which is heavily affected by the imbalanced distribution of the classes in a manually annotated data set of non-native English. In order to address problems caused by this extreme class imbalance, methods for cost-sensitive learning (weighting inversely proportional to class frequencies) and over-sampling of synthetic instances (SMOTE) are investigated in order to improve classification performance. Experiments using classifiers consisting of features based on acoustic phonetics and word identity demonstrate that these machine learning approaches lead to performance improvements over the baseline system based on the extremely imbalanced data. In addition, several different types of classifiers were compared. Finally, the paper analyzes the robustness of classifier performance across different phones.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129067618","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: 17
Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings 通过神经词嵌入丰富语义,动态支持会话交互中未探索的领域
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078640
Yun-Nung (Vivian) Chen, Alexander I. Rudnicky
{"title":"Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings","authors":"Yun-Nung (Vivian) Chen, Alexander I. Rudnicky","doi":"10.1109/SLT.2014.7078640","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078640","url":null,"abstract":"Spoken language interfaces are being incorporated into various devices (e.g. smart-phones, smart TVs, etc). However, current technology typically limits conversational interactions to a few narrow predefined domains/topics. For example, dialogue systems for smartphone operation fail to respond when users ask for functions not supported by currently installed applications. We propose to dynamically add application-based domains according to users' requests by using descriptions of applications as a retrieval cue to find relevant applications. The approach uses structured knowledge resources (e.g. Freebase, Wikipedia, FrameNet) to induce types of slots for generating semantic seeds, and enriches the semantics of spoken queries with neural word embeddings, where semantically related concepts can be additionally included for acquiring knowledge that does not exist in the predefined domains. The system can then retrieve relevant applications or dynamically suggest users install applications that support unexplored domains. We find that vendor descriptions provide a reliable source of information for this purpose.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129227125","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: 28
Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as features 以子空间高斯混合模型的状态投影向量为特征改进深度神经网络
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078562
B. MuraliKarthick, S. Umesh
{"title":"Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as features","authors":"B. MuraliKarthick, S. Umesh","doi":"10.1109/SLT.2014.7078562","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078562","url":null,"abstract":"Recent advancement in deep neural network (DNN) has surpassed the conventional hidden Markov model-Gaussian mixture model (HMM-GMM) framework due to its efficient training procedure. Providing better phonetic context information in the input gives improved performance for DNN. The state projection vectors (state specific vectors) in subspace Gaussian mixture model (SGMM) captures the phonetic information in low dimensional vector space. In this paper, we propose to use state specific vectors of SGMM as features thereby providing additional phonetic information for the DNN framework. To each observation vector in the train data, the corresponding state specific vectors of SGMM are aligned to form the state specific vector feature set. Linear discriminant analysis (LDA) feature set are formed by applying LDA to the training data. Since bottleneck features are efficient in extracting useful discriminative information for the phonemes, LDA feature set and state specific vector feature set are converted to bottleneck features. These bottleneck features of both feature sets act as input features to train a single DNN framework. Relative improvement of 8.8% for TIMIT database (core test set) and 9.7% for WSJ corpus is obtained by using the state specific vector bottleneck feature set when compared to the DNN trained only with LDA bottleneck feature set. Also training Deep belief network - DNN (DBN-DNN) using the proposed feature set attains a WER of 20.46% on TIMIT core test set proving the effectiveness of our method. The state specific vectors while acting as features, provide additional useful information related to phoneme variation. Thus by combining it with LDA bottleneck features improved performance is obtained using the DNN framework.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128045881","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: 1
Context-based recognition network adaptation for improving on-line ASR in Air Traffic Control 基于上下文的识别网络自适应改进空中交通管制在线自动识别
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078542
Anna Schmidt, Youssef Oualil, O. Ohneiser, Matthias Kleinert, Marc Schulder, Arif Khan, H. Helmke, D. Klakow
{"title":"Context-based recognition network adaptation for improving on-line ASR in Air Traffic Control","authors":"Anna Schmidt, Youssef Oualil, O. Ohneiser, Matthias Kleinert, Marc Schulder, Arif Khan, H. Helmke, D. Klakow","doi":"10.1109/SLT.2014.7078542","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078542","url":null,"abstract":"This paper presents an approach for incorporating situational context information into an on-line Automatic Speech Recognition (ASR) component of an Air Traffic Control (ATC) assistance system to improve recognition performance. Context information is treated as prior information to reduce the search space for recognition. It is integrated in the ASR pipeline by continually updating the recognition network. This is achieved by automatically adapting the underlying grammar whenever new situational knowledge becomes available. The context-dependent recognition network is then re-created and substituted for recognition based on these context-dependent grammars. As a result, the recognizer's search space is constantly being limited to that subset of hypotheses that are deemed plausible in the current situation. Since recognition and adaptation tasks can be easily performed by two separate parallel processes, on-line capabilities of the system are maintained, and response times do not increase as a result of context integration. Experiments conducted on about two hours of ATC data show a reduction in command error rate by a factor of three when context is used.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127966075","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
Artificial neural network features for speaker diarization 人工神经网络特征的扬声器拨号
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078608
S. Yella, A. Stolcke, M. Slaney
{"title":"Artificial neural network features for speaker diarization","authors":"S. Yella, A. Stolcke, M. Slaney","doi":"10.1109/SLT.2014.7078608","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078608","url":null,"abstract":"Speaker diarization finds contiguous speaker segments in an audio recording and clusters them by speaker identity, without any a-priori knowledge. Diarization is typically based on short-term spectral features such as Mel-frequency cepstral coefficients (MFCCs). Though these features carry average information about the vocal tract characteristics of a speaker, they are also susceptible to factors unrelated to the speaker identity. In this study, we propose an artificial neural network (ANN) architecture to learn a feature transform that is optimized for speaker diarization. We train a multi-hidden-layer ANN to judge whether two given speech segments came from the same or different speakers, using a shared transform of the input features that feeds into a bottleneck layer. We then use the bottleneck layer activations as features, either alone or in combination with baseline MFCC features in a multistream mode, for speaker diarization on test data. The resulting system is evaluated on various corpora of multi-party meetings. A combination of MFCC and ANN features gives up to 14% relative reduction in diarization error, demonstrating that these features are providing an additional independent source of knowledge.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131964228","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: 48
Effective combination of heterogeneous subword-based spoken term detection systems 基于异构子词的口语词检测系统的有效组合
2014 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2014-12-01 DOI: 10.1109/SLT.2014.7078614
Shi-wook Lee, Kazuyo Tanaka, Y. Itoh
{"title":"Effective combination of heterogeneous subword-based spoken term detection systems","authors":"Shi-wook Lee, Kazuyo Tanaka, Y. Itoh","doi":"10.1109/SLT.2014.7078614","DOIUrl":"https://doi.org/10.1109/SLT.2014.7078614","url":null,"abstract":"Combining heterogeneous systems has been shown to provide significant improvement in the spoken term detection (STD) task. However, there has been little research into why the system combination improves STD performance. In this paper, we analyze the heterogeneousness of the systems by calculating the correlation between their scores and evaluating the effectiveness of the combined subword-based systems. Here, we investigate both heterogeneous detection schemes and heterogeneous subword units, using a test-bed of NTCIR-10 task. Experimental analysis shows that the higher improvement rates can be achieved by combining the more heterogeneous systems which are with lower correlation each other, that is, with lager amount of complementary information. Compared with the highest performance among each individual system to be combined, a parallel combination of heterogeneous subword units improves the STD performance by 13.59%, and the system with an efficient cascaded combination of heterogeneous subword units and heterogeneous detection schemes improves by 12.79%. Finally, the state-of-the-art performance of 74.07 average maximum F-measure on the NTCIR-10 task can be achieved by the combination of heterogeneous subword units and heterogeneous detection schemes.","PeriodicalId":160484,"journal":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127644662","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
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
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