2012 IEEE Spoken Language Technology Workshop (SLT)最新文献_第4页

Synthesizing expressive speech from amateur audiobook recordings 从业余有声读物录音中合成富有表现力的言语

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424239

Éva Székely, T. Csapó, B. Tóth, P. Mihajlik, Julie Carson-Berndsen

{"title":"Synthesizing expressive speech from amateur audiobook recordings","authors":"Éva Székely, T. Csapó, B. Tóth, P. Mihajlik, Julie Carson-Berndsen","doi":"10.1109/SLT.2012.6424239","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424239","url":null,"abstract":"Freely available audiobooks are a rich resource of expressive speech recordings that can be used for the purposes of speech synthesis. Natural sounding, expressive synthetic voices have previously been built from audiobooks that contained large amounts of highly expressive speech recorded from a professionally trained speaker. The majority of freely available audiobooks, however, are read by amateur speakers, are shorter and contain less expressive (less emphatic, less emotional, etc.) speech both in terms of quality and quantity. Synthesizing expressive speech from a typical online audiobook therefore poses many challenges. In this work we address these challenges by applying a method consisting of minimally supervised techniques to align the text with the recorded speech, select groups of expressive speech segments and build expressive voices for hidden Markov-model based synthesis using speaker adaptation. Subjective listening tests have shown that the expressive synthetic speech generated with this method is often able to produce utterances suited to an emotional message. We used a restricted amount of speech data in our experiment, in order to show that the method is generally applicable to most typical audiobooks widely available online.","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":"132335605","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: 18

A nonparametric Bayesian approach to learning multimodal interaction management 学习多模态交互管理的非参数贝叶斯方法

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424162

Zhuoran Wang, Oliver Lemon

{"title":"A nonparametric Bayesian approach to learning multimodal interaction management","authors":"Zhuoran Wang, Oliver Lemon","doi":"10.1109/SLT.2012.6424162","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424162","url":null,"abstract":"Managing multimodal interactions between humans and computer systems requires a combination of state estimation based on multiple observation streams, and optimisation of time-dependent action selection. Previous work using partially observable Markov decision processes (POMDPs) for multimodal interaction has focused on simple turn-based systems. However, state persistence and implicit state transitions are frequent in real-world multimodal interactions. These phenomena cannot be fully modelled using turn-based systems, where the timing of system actions is a non-trivial issue. In addition, in prior work the POMDP parameterisation has been either hand-coded or learned from labelled data, which requires significant domain-specific knowledge and is labor-consuming. We therefore propose a nonparametric Bayesian method to automatically infer the (distributional) representations of POMDP states for multimodal interactive systems, without using any domain knowledge. We develop an extended version of the infinite POMDP method, to better address state persistence, implicit transition, and timing issues observed in real data. The main contribution is a “sticky” infinite POMDP model that is biased towards self-transitions. The performance of the proposed unsupervised approach is evaluated based on both artificially synthesised data and a manually transcribed and annotated human-human interaction corpus. We show statistically significant improvements (e.g. in ability of the planner to recall human bartender actions) over a supervised POMDP method.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"42 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":"122951428","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

Adaptation of context-dependent deep neural networks for automatic speech recognition 上下文相关深度神经网络在自动语音识别中的自适应

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424251

K. Yao, Dong Yu, F. Seide, Hang Su, L. Deng, Y. Gong

引用次数: 210

Automatic Chinese pronunciation error detection using SVM trained with structural features 基于结构特征训练的支持向量机中文发音错误自动检测

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424270

Tongmu Zhao, A. Hoshino, Masayuki Suzuki, N. Minematsu, K. Hirose

引用次数: 24

Acoustic modeling for under-resourced languages based on vectorial HMM-states representation using Subspace Gaussian Mixture Models 基于子空间高斯混合模型的向量hmm状态表示的资源不足语言声学建模

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424245

Mohamed Bouallegue, Emmanuel Ferreira, D. Matrouf, G. Linarès, Maria Goudi, P. Nocera

引用次数: 2

Two-layer mutually reinforced random walk for improved multi-party meeting summarization 改进多方会议摘要的两层相互强化随机漫步

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424268

Yun-Nung (Vivian) Chen, Florian Metze

引用次数: 28

Reactive and continuous control of HMM-based speech synthesis 基于hmm的语音合成反应和连续控制

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424231

M. Astrinaki, N. D'Alessandro, B. Picart, Thomas Drugman, T. Dutoit

引用次数: 26

Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR 基于dnn的LVCSR中的无监督跨语言知识迁移

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424230

P. Swietojanski, Arnab Ghoshal, S. Renals

引用次数: 146

Improving large vocabulary continuous speech recognition by combining GMM-based and reservoir-based acoustic modeling 结合基于gmm和基于储层的声学建模改进大词汇量连续语音识别

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424206

Fabian Triefenbach, Kris Demuynck, J. Martens

引用次数: 5

Class-based speech recognition using a maximum dissimilarity criterion and a tolerance classification margin 基于类的语音识别使用最大不相似度准则和容忍分类裕度

2012 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2012-12-01 DOI: 10.1109/SLT.2012.6424203

Arsenii Gorin, D. Jouvet

引用次数: 4