2016 IEEE Spoken Language Technology Workshop (SLT)最新文献_第3页

Improved prediction of the accent gap between speakers of English for individual-based clustering of World Englishes 改进了基于个体的世界英语聚类的英语说话者之间的口音差距预测

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846255

Fumiya Shiozawa, D. Saito, N. Minematsu

{"title":"Improved prediction of the accent gap between speakers of English for individual-based clustering of World Englishes","authors":"Fumiya Shiozawa, D. Saito, N. Minematsu","doi":"10.1109/SLT.2016.7846255","DOIUrl":"https://doi.org/10.1109/SLT.2016.7846255","url":null,"abstract":"The term of “World Englishes” describes the current state of English and one of their main characteristics is a large diversity of pronunciation, called accents. In our previous studies, we developed several techniques to realize effective clustering and visualization of the diversity. For this aim, the accent gap between two speakers has to be quantified independently of extra-linguistic factors such as age and gender. To realize this, a unique representation of speech, called speech structure, which is theoretically invariant against these factors, was applied to represent pronunciation. In the current study, by controlling the degree of invariance, we attempt to improve accent gap prediction. Two techniques are tested: DNN-based model-free estimation of divergence and multi-stream speech structures. In the former, instead of estimating separability between two speech events based on some model assumptions, DNN-based class posteriors are utilized for estimation. In the latter, by deriving one speech structure for each sub-space of acoustic features, constrained invariance is realized. Our proposals are tested in terms of the correlation between reference accent gaps and the predicted and quantified gaps. Experiments show that the correlation is improved from 0.718 to 0.730.","PeriodicalId":281635,"journal":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129088224","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

Automatic optimization of data perturbation distributions for multi-style training in speech recognition 语音识别中多风格训练数据扰动分布的自动优化

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846240

Mortaza Doulaty, R. Rose, O. Siohan

{"title":"Automatic optimization of data perturbation distributions for multi-style training in speech recognition","authors":"Mortaza Doulaty, R. Rose, O. Siohan","doi":"10.1109/SLT.2016.7846240","DOIUrl":"https://doi.org/10.1109/SLT.2016.7846240","url":null,"abstract":"Speech recognition performance using deep neural network based acoustic models is known to degrade when the acoustic environment and the speaker population in the target utterances are significantly different from the conditions represented in the training data. To address these mismatched scenarios, multi-style training (MTR) has been used to perturb utterances in an existing uncorrupted and potentially mismatched training speech corpus to better match target domain utterances. This paper addresses the problem of determining the distribution of perturbation levels for a given set of perturbation types that best matches the target speech utterances. An approach is presented that, given a small set of utterances from a target domain, automatically identifies an empirical distribution of perturbation levels that can be applied to utterances in an existing training set. Distributions are estimated for perturbation types that include acoustic background environments, reverberant room configurations, and speaker related variation like frequency and temporal warping. The end goal is for the resulting perturbed training set to characterize the variability in the target domain and thereby optimize ASR performance. An experimental study is performed to evaluate the impact of this approach on ASR performance when the target utterances are taken from a simulated far-field acoustic environment.","PeriodicalId":281635,"journal":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114923030","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

Improving multi-stream classification by mapping sequence-embedding in a high dimensional space 利用高维空间映射序列嵌入改进多流分类

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846269

Mohamed Bouaziz, Mohamed Morchid, Richard Dufour, G. Linarès

{"title":"Improving multi-stream classification by mapping sequence-embedding in a high dimensional space","authors":"Mohamed Bouaziz, Mohamed Morchid, Richard Dufour, G. Linarès","doi":"10.1109/SLT.2016.7846269","DOIUrl":"https://doi.org/10.1109/SLT.2016.7846269","url":null,"abstract":"Most of the Natural and Spoken Language Processing tasks now employ Neural Networks (NN), allowing them to reach impressive performances. Embedding features allow the NLP systems to represent input vectors in a latent space and to improve the observed performances. In this context, Recurrent Neural Network (RNN) based architectures such as Long Short-Term Memory (LSTM) are well known for their capacity to encode sequential data into a non-sequential hidden vector representation, called sequence embedding. In this paper, we propose an LSTM-based multi-stream sequence embedding in order to encode parallel sequences by a single non-sequential latent representation vector. We then propose to map this embedding representation in a high-dimensional space using a Support Vector Machine (SVM) in order to classify the multi-stream sequences by finding out an optimal hyperplane. Multi-stream sequence embedding allowed the SVM classifier to more efficiently profit from information carried by both parallel streams and longer sequences. The system achieved the best performance, in a multi-stream sequence classification task, with a gain of 9 points in error rate compared to an SVM trained on the original input sequences.","PeriodicalId":281635,"journal":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114891322","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

A log-linear weighting approach in the Word2vec space for spoken language understanding 用于口语理解的Word2vec空间的对数线性加权方法

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846289

Killian Janod, Mohamed Morchid, Richard Dufour, G. Linarès

引用次数: 3

Influence of corpus size and content on the perceptual quality of a unit selection MaryTTS voice 语料库大小和内容对单元选择MaryTTS语音感知质量的影响

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846336

Florian Hinterleitner, Benjamin Weiss, S. Möller

引用次数: 2

Automatic plagiarism detection for spoken responses in an assessment of English language proficiency 英语语言能力评估中口语回答的自动抄袭检测

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846254

Xinhao Wang, Keelan Evanini, James V. Bruno, Matthew David Mulholland

引用次数: 8

Robust utterance classification using multiple classifiers in the presence of speech recognition errors 基于多分类器的语音识别错误鲁棒性语音分类

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846291

Takeshi Homma, Kazuaki Shima, Takuya Matsumoto

引用次数: 2

Automatic turn segmentation for Movie & TV subtitles 自动转向分割电影和电视字幕

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846272

Pierre Lison, R. Meena

引用次数: 23

End-to-End attention based text-dependent speaker verification 基于端到端注意的文本依赖说话人验证

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846261

Shi-Xiong Zhang, Zhuo Chen, Yong Zhao, Jinyu Li, Y. Gong

{"title":"End-to-End attention based text-dependent speaker verification","authors":"Shi-Xiong Zhang, Zhuo Chen, Yong Zhao, Jinyu Li, Y. Gong","doi":"10.1109/SLT.2016.7846261","DOIUrl":"https://doi.org/10.1109/SLT.2016.7846261","url":null,"abstract":"A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetic discriminate/speaker discriminate DNN as a feature extractor for speaker verification has shown promising results. The extracted frame-level (bottleneck, posterior or d-vector) features are equally weighted and aggregated to compute an utterance-level speaker representation (d-vector or i-vector). In this work we use a speaker discriminate CNN to extract the noise-robust frame-level features. These features are smartly combined to form an utterance-level speaker vector through an attention mechanism. The proposed attention model takes the speaker discriminate information and the phonetic information to learn the weights. The whole system, including the CNN and attention model, is joint optimized using an end-to-end criterion. The training algorithm imitates exactly the evaluation process — directly mapping a test utterance and a few target speaker utterances into a single verification score. The algorithm can smartly select the most similar impostor for each target speaker to train the network. We demonstrated the effectiveness of the proposed end-to-end system on Windows 10 “Hey Cortana” speaker verification task.","PeriodicalId":281635,"journal":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114651716","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: 173

Attribute based shared hidden layers for cross-language knowledge transfer 基于属性的跨语言知识传递共享隐藏层

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846327

Vipul Arora, A. Lahiri, Henning Reetz

引用次数: 2