2016 IEEE Spoken Language Technology Workshop (SLT)最新文献_第6页

Multimodal deep neural nets for detecting humor in TV sitcoms 电视情景喜剧幽默检测的多模态深度神经网络

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846293

D. Bertero, Pascale Fung

引用次数: 5

I-Vector estimation as auxiliary task for Multi-Task Learning based acoustic modeling for automatic speech recognition 基于多任务学习声学建模的语音自动识别辅助任务i-向量估计

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846237

Gueorgui Pironkov, S. Dupont, T. Dutoit

{"title":"I-Vector estimation as auxiliary task for Multi-Task Learning based acoustic modeling for automatic speech recognition","authors":"Gueorgui Pironkov, S. Dupont, T. Dutoit","doi":"10.1109/SLT.2016.7846237","DOIUrl":"https://doi.org/10.1109/SLT.2016.7846237","url":null,"abstract":"I-Vectors have been successfully applied in the speaker identification community in order to characterize the speaker and its acoustic environment. Recently, i-vectors have also shown their usefulness in automatic speech recognition, when concatenated to standard acoustic features. Instead of directly feeding the acoustic model with i-vectors, we here investigate a Multi-Task Learning approach, where a neural network is trained to simultaneously recognize the phone-state posterior probabilities and extract i-vectors, using the standard acoustic features. Multi-Task Learning is a regularization method which aims at improving the network's generalization ability, by training a unique network to solve several different, but related tasks. The core idea of using i-vector extraction as an auxiliary task is to give the network an additional inter-speaker awareness, and thus, reduce overfitting. Overfitting is a commonly met issue in speech recognition and is especially impacting when the amount of training data is limited. The proposed setup is trained and tested on the TIMIT database, while the acoustic modeling is performed using a Recurrent Neural Network with Long Short-Term Memory cells.","PeriodicalId":281635,"journal":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","volume":"17 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":"121665401","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: 3

The MSIIP system for dialog state tracking challenge 5 MSIIP系统对对话状态跟踪的挑战5

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846313

Ying Su, Miao Li, Ji Wu

引用次数: 1

Neural dialog state tracker for large ontologies by attention mechanism 基于注意机制的大型本体神经对话状态跟踪

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846314

Youngsoo Jang, Jiyeon Ham, Byung-Jun Lee, Youngjae Chang, Kee-Eung Kim

引用次数: 17

Performance monitoring for automatic speech recognition in noisy multi-channel environments 噪声多通道环境下自动语音识别的性能监测

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846244

B. Meyer, Sri Harish Reddy Mallidi, Angel Mario Castro Martinez, G. P. Vayá, H. Kayser, H. Hermansky

引用次数: 16

LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic challenge 2016年多类型广播阿拉伯语挑战赛LIUM ASR系统

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846278

N. Tomashenko, Kevin Vythelingum, Anthony Rousseau, Y. Estève

引用次数: 17

Multilingual BLSTM and speaker-specific vector adaptation in 2016 but babel system 2016年多语言BLSTM和特定说话人的载体适应，但巴别塔系统

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846330

M. Karafiát, M. Baskar, P. Matejka, Karel Veselý, F. Grézl, J. Černocký

引用次数: 23

Unsupervised k-means clustering based out-of-set candidate selection for robust open-set language recognition 基于无监督k均值聚类的鲁棒开集语言识别的集外候选选择

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846284

Qian Zhang, J. Hansen

{"title":"Unsupervised k-means clustering based out-of-set candidate selection for robust open-set language recognition","authors":"Qian Zhang, J. Hansen","doi":"10.1109/SLT.2016.7846284","DOIUrl":"https://doi.org/10.1109/SLT.2016.7846284","url":null,"abstract":"Research in open-set language identification (LID) generally focuses more on accurate in-set language modeling versus improved out-of-set (OOS) language rejection. The main reason for this is the increased cost/resources in collecting sufficient OOS data, versus the in-set languages of interest. Therefore, unknown or OOS language rejection is a challenge. To address this through efficient data collection, we propose a flexible OOS candidate selection method for universal OOS language coverage. Since state-of-the-art i-vector system followed by generative Gaussian back-end achieves effective performance for LID, the selected K candidates are expected to be general enough to represent the entire OOS language space. Therefore, an unsupervised k-means clustering approach is proposed for effective OOS candidate selection. This method is evaluated on a dataset derived from a large-scale corpus (LRE-09) which contains 40 languages. With the proposed selection method, the total OOS training diversity can be reduced by 89% and still achieve better performance on both OOS rejection and overall classification. The proposed method also shows clear benefits for greater data enhancement. Therefore, the proposed solution achieves sustained performance with the advantage of employing a minimum number of OOS language candidates efficiently.","PeriodicalId":281635,"journal":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","volume":"29 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":"122079642","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

F0 transformation techniques for statistical voice conversion with direct waveform modification with spectral differential F0变换技术的统计语音转换与直接波形修改与频谱微分

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846338

Kazuhiro Kobayashi, T. Toda, Satoshi Nakamura

{"title":"F0 transformation techniques for statistical voice conversion with direct waveform modification with spectral differential","authors":"Kazuhiro Kobayashi, T. Toda, Satoshi Nakamura","doi":"10.1109/SLT.2016.7846338","DOIUrl":"https://doi.org/10.1109/SLT.2016.7846338","url":null,"abstract":"This paper presents several F0 transformation techniques for statistical voice conversion (VC) with direct waveform modification with spectral differential (DIFFVC). Statistical VC is a technique to convert speaker identity of a source speaker's voice into that of a target speaker by converting several acoustic features, such as spectral and excitation features. This technique usually uses vocoder to generate converted speech waveforms from the converted acoustic features. However, the use of vocoder often causes speech quality degradation of the converted voice owing to insufficient parameterization accuracy. To avoid this issue, we have proposed a direct waveform modification technique based on spectral differential filtering and have successfully applied it to intra-gender singing VC (DIFFSVC) where excitation features are not necessary converted. Moreover, we have also applied it to cross-gender singing VC by implementing F0 transformation with a constant rate such as one octave increase or decrease. On the other hand, it is not straightforward to apply the DIFFSVC framework to normal speech conversion because the F0 transformation ratio widely varies depending on a combination of the source and target speakers. In this paper, we propose several F0 transformation techniques for DIFFVC and compare their performance in terms of speech quality of the converted voice and conversion accuracy of speaker individuality. The experimental results demonstrate that the F0 transformation technique based on waveform modification achieves the best performance among the proposed techniques.","PeriodicalId":281635,"journal":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","volume":"10 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":"132188743","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: 16

Analysis of the DNN-based SRE systems in multi-language conditions 多语言条件下基于dnn的SRE系统分析

2016 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2016-12-01 DOI: 10.1109/SLT.2016.7846265

Ondrej Novotný, P. Matejka, O. Glembek, Oldrich Plchot, F. Grézl, L. Burget, J. Černocký

引用次数: 10