2013 IEEE International Conference on Acoustics, Speech and Signal Processing最新文献_第7页

A low-power VGA full-frame feature extraction processor 低功耗VGA全帧特征提取处理器

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638152

Don-Guk Jeon, Yejoong Kim, Inhee Lee, Zhengya Zhang, D. Blaauw, D. Sylvester

引用次数: 2

Open-set semi-supervised audio-visual speaker recognition using co-training LDA and Sparse Representation Classifiers 基于联合训练LDA和稀疏表示分类器的开集半监督视听说话人识别

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638208

Xuran Zhao, N. Evans, J. Dugelay

引用次数: 2

Data centric multi-shift sensor scheduling for wireless sensor networks 无线传感器网络中以数据为中心的多位移传感器调度

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638530

Jialin Zhang, Y. Hu

引用次数: 3

Direct product based deep belief networks for automatic speech recognition 直接产品为基础的深度信念网络自动语音识别

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638238

P. Fousek, Steven J. Rennie, Pierre L. Dognin, V. Goel

{"title":"Direct product based deep belief networks for automatic speech recognition","authors":"P. Fousek, Steven J. Rennie, Pierre L. Dognin, V. Goel","doi":"10.1109/ICASSP.2013.6638238","DOIUrl":"https://doi.org/10.1109/ICASSP.2013.6638238","url":null,"abstract":"In this paper, we present new methods for parameterizing the connections of neural networks using sums of direct products. We show that low rank parameterizations of weight matrices are a subset of this set, and explore the theoretical and practical benefits of representing weight matrices using sums of Kronecker products. ASR results on a 50 hr subset of the English Broadcast News corpus indicate that the approach is promising. In particular, we show that a factorial network with more than 150 times less parameters in its bottom layer than its standard unconstrained counterpart suffers minimal WER degradation, and that by using sums of Kronecker products, we can close the gap in WER performance while maintaining very significant parameter savings. In addition, direct product DBNs consistently outperform standard DBNs with the same number of parameters. These results have important implications for research on deep belief networks (DBNs). They imply that we should be able to train neural networks with thousands of neurons and minimal restrictions much more rapidly than is currently possible, and that by using sums of direct products, it will be possible to train neural networks with literally millions of neurons tractably-an exciting prospect.","PeriodicalId":183968,"journal":{"name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","volume":"379 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116579436","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

Acoustic channel model for adaptive downhole communication over deep drill strings 深钻柱自适应井下通信的声通道模型

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638589

M. Gutierrez-Estevez, U. Krüger, K. Krueger, K. Manolakis, V. Jungnickel

{"title":"Acoustic channel model for adaptive downhole communication over deep drill strings","authors":"M. Gutierrez-Estevez, U. Krüger, K. Krueger, K. Manolakis, V. Jungnickel","doi":"10.1109/ICASSP.2013.6638589","DOIUrl":"https://doi.org/10.1109/ICASSP.2013.6638589","url":null,"abstract":"For reducing costs in drilling technology, seismic prediction while drilling (SPWD) is envisioned. SPWD needs a fast data link bringing up the seismic data from bottomhole to the ground. In this paper, we propose a flexible and easy-to-use acoustic channel model for long drill strings. The model enables efficient design of adaptive OFDM communication links and prediction of achievable data rates for variable string dimensions. We describe acoustic wave propagation by the S-parameters of the drill string modelled as a series of alternating short and long resonators due to segments of constant acoustic impedance. All segments have been parametrised and the final channel is a concatenation of all its segments. We verify the new model by comparison with measurements on a 55 m long drill string. By using our model, the properties of a manifold of real drill pipes with variable dimensions can be predicted. We investigate the impact of length variations typical for rough drilling applications. For efficient communications over 1.5 km, length variations of the screwed tool joints should be limited to a few centimetres while the pipe length may vary up to one meter.","PeriodicalId":183968,"journal":{"name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122764361","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

Behavior of greedy sparse representation algorithms on nested supports 嵌套支架上贪婪稀疏表示算法的行为

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638758

B. Mailhé, Bob L. Sturm, Mark D. Plumbley

引用次数: 3

An advanced feature compensation method employing acoustic model with phonetically constrained structure 一种基于语音约束结构声学模型的高级特征补偿方法

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6639036

Wooil Kim, J. Hansen

引用次数: 2

Exemplar based language recognition method for short-duration speech segments 基于范例的短时间语音片段语言识别方法

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6639091

Meng-Ge Wang, Yan Song, B. Jiang, Lirong Dai, I. Mcloughlin

引用次数: 9

Emotion classification via utterance-level dynamics: A pattern-based approach to characterizing affective expressions 基于话语层次动态的情感分类:一种基于模式的情感表达表征方法

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638344

Yelin Kim, E. Provost

{"title":"Emotion classification via utterance-level dynamics: A pattern-based approach to characterizing affective expressions","authors":"Yelin Kim, E. Provost","doi":"10.1109/ICASSP.2013.6638344","DOIUrl":"https://doi.org/10.1109/ICASSP.2013.6638344","url":null,"abstract":"Human emotion changes continuously and sequentially. This results in dynamics intrinsic to affective communication. One of the goals of automatic emotion recognition research is to computationally represent and analyze these dynamic patterns. In this work, we focus on the global utterance-level dynamics. We are motivated by the hypothesis that global dynamics have emotion-specific variations that can be used to differentiate between emotion classes. Consequently, classification systems that focus on these patterns will be able to make accurate emotional assessments. We quantitatively represent emotion flow within an utterance by estimating short-time affective characteristics. We compare time-series estimates of these characteristics using Dynamic Time Warping, a time-series similarity measure. We demonstrate that this similarity can effectively recognize the affective label of the utterance. The similarity-based pattern modeling outperforms both a feature-based baseline and static modeling. It also provides insight into typical high-level patterns of emotion. We visualize these dynamic patterns and the similarities between the patterns to gain insight into the nature of emotion expression.","PeriodicalId":183968,"journal":{"name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122911711","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: 70

Graph based multimodal word clustering for video event detection 基于图的多模态词聚类视频事件检测

2013 IEEE International Conference on Acoustics, Speech and Signal Processing Pub Date : 2013-05-26 DOI: 10.1109/ICASSP.2013.6638342

Aravind Namandi Vembu, P. Natarajan, Shuang Wu, R. Prasad, P. Natarajan

引用次数: 2