2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).最新文献

Environmental sniffing: noise knowledge estimation for robust speech systems 环境嗅探:鲁棒语音系统的噪声知识估计

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2007-02-01 DOI: 10.1109/ICASSP.2003.1202307

Murat Akbacak, J. Hansen

{"title":"Environmental sniffing: noise knowledge estimation for robust speech systems","authors":"Murat Akbacak, J. Hansen","doi":"10.1109/ICASSP.2003.1202307","DOIUrl":"https://doi.org/10.1109/ICASSP.2003.1202307","url":null,"abstract":"We propose a framework for extracting knowledge about environmental noise from an input audio sequence and organizing this knowledge for use by other speech systems. To date, most approaches dealing with environmental noise in speech systems are based on assumptions about the noise, or differences in the collection of and training on a specific noise condition, rather than exploring the nature of the noise. We are interested in constructing a new speech framework, entitled environmental sniffing, to detect, classify and track acoustic environmental conditions. The first goal of the framework is to seek out detailed information about the environmental characteristics instead of just detecting environmental changes. The second goal is to organize this knowledge in an effective manner to allow smart decisions to direct other speech systems. Our current framework uses a number of speech processing modules including the Teager energy operator (TEO) and a hybrid algorithm with T/sup 2/-BIC segmentation, noise language modeling and GMM classification in noise knowledge estimation. We define a new information criterion that incorporates the impact of noise on environmental sniffing performance. We use an in-vehicle speech and noise environment as a test platform for our evaluations and investigate the integration of environmental sniffing into an automatic speech recognition (ASR) engine in this environment. Noise classification experiments show that the hybrid algorithm achieves an error rate of 25.51%, outperforming a baseline system by an absolute 7.08%.","PeriodicalId":104473,"journal":{"name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128863942","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: 23

Wideband array signal processing using MCMC methods 宽带阵列信号处理的MCMC方法

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2005-02-01 DOI: 10.1109/ICASSP.2003.1199900

W. Ng, J. Reilly, T. Kirubarajan, Jean-René Larocque

引用次数: 16

Speech enhancement based on the general transfer function GSC and postfiltering 基于通用传递函数GSC和后滤波的语音增强

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2004-10-18 DOI: 10.1109/ICASSP.2003.1198929

S. Gannot, I. Cohen

{"title":"Speech enhancement based on the general transfer function GSC and postfiltering","authors":"S. Gannot, I. Cohen","doi":"10.1109/ICASSP.2003.1198929","DOIUrl":"https://doi.org/10.1109/ICASSP.2003.1198929","url":null,"abstract":"In speech enhancement applications, microphone array postfiltering allows additional reduction of noise components at a beamformer output. Among microphone array structures, the recently proposed general transfer function generalized sidelobe canceller (TF-GSC) has shown impressive noise reduction abilities in a directional noise field, while still maintaining low speech distortion. However, in a diffused noise field, less significant noise reduction is obtainable. The performance is even further degraded when the noise is nonstationary. We present three postfiltering methods for improving the performance of microphone arrays. Two of them are based on single-channel speech enhancers and make use of recently proposed algorithms concatenated to the beamformer output. The third is a multichannel speech enhancer which exploits noise-only components constructed within the TF-GSC structure. An experimental study, which consists of both objective and subjective evaluation in various noise fields, demonstrates the advantage of the multi-channel postfiltering compared to single-channel techniques.","PeriodicalId":104473,"journal":{"name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121590161","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: 122

Group delay approximation of allpass digital filters by transforming the desired response 通过变换期望响应的全通数字滤波器群延迟逼近

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2004-07-25 DOI: 10.1109/ICASSP.2003.1201701

T. Matsunaga, M. Ikehara

引用次数: 1

Mixtures of inverse covariances 逆协方差的混合

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2004-04-19 DOI: 10.1109/ICASSP.2003.1198915

Vincent Vanhoucke, Ananth Sankar

引用次数: 27

Robust variational speech separation using fewer microphones than speakers 鲁棒变分语音分离使用较少的麦克风比扬声器

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2003-07-06 DOI: 10.1109/ICASSP.2003.1198723

Steven J. Rennie, P. Aarabi, T. Kristjansson, B. Frey, Kannan Achan

引用次数: 7

A trainable retrieval system for cartoon character images 一种可训练的卡通人物图像检索系统

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2003-07-06 DOI: 10.1109/ICASSP.2003.1199564

M. Haseyama, Atsushi Matsumura

引用次数: 4

Robust cephalometric landmark identification using support vector machines 基于支持向量机的鲁棒头颅测量地标识别

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2003-07-06 DOI: 10.1109/ICASSP.2003.1202494

S. Chakrabartty, M. Yagi, T. Shibata, G. Cauwenberghs

引用次数: 18

Comparing MFCC and MPEG-7 audio features for feature extraction, maximum likelihood HMM and entropic prior HMM for sports audio classification 比较MFCC和MPEG-7音频特征提取、最大似然HMM和熵先验HMM对运动音频分类的影响

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2003-07-06 DOI: 10.1109/ICASSP.2003.1200048

Ziyou Xiong, R. Radhakrishnan, Ajay Divakaran, Thomas S. Huang

引用次数: 35

Real-time adaptive background segmentation 实时自适应背景分割

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). Pub Date : 2003-07-06 DOI: 10.1109/ICASSP.2003.1199481

D. Butler, S. Sridharan, V. Bove

引用次数: 34