Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.859162
K. Yao, Bertram E. Shi, Pascale Fung, Z. Cao
We present a model-based noise compensation algorithm for robust speech recognition in nonstationary noisy environments. The effect of noise is split into a stationary part, compensated by parallel model combination, and a time varying residual. The evolution of residual noise parameters is represented by a set of state space models. The state space models are updated by Kalman prediction and the sequential maximum likelihood algorithm. Prediction of residual noise parameters from different mixtures are fused, and the fused noise parameters are used to modify the linearized likelihood score of each mixture. Noise compensation proceeds in parallel with recognition. Experimental results demonstrate that the proposed algorithm improves recognition performance in highly nonstationary environments, compared with parallel model combination alone.
{"title":"Residual noise compensation for robust speech recognition in nonstationary noise","authors":"K. Yao, Bertram E. Shi, Pascale Fung, Z. Cao","doi":"10.1109/ICASSP.2000.859162","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.859162","url":null,"abstract":"We present a model-based noise compensation algorithm for robust speech recognition in nonstationary noisy environments. The effect of noise is split into a stationary part, compensated by parallel model combination, and a time varying residual. The evolution of residual noise parameters is represented by a set of state space models. The state space models are updated by Kalman prediction and the sequential maximum likelihood algorithm. Prediction of residual noise parameters from different mixtures are fused, and the fused noise parameters are used to modify the linearized likelihood score of each mixture. Noise compensation proceeds in parallel with recognition. Experimental results demonstrate that the proposed algorithm improves recognition performance in highly nonstationary environments, compared with parallel model combination alone.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131348727","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.861164
M. Schubert, H. Boche
Downlink beamforming has been proposed for high-capacity and spectrally-efficient DS-CDMA wireless systems. It mitigates the effects of multiple access interference, self interference and inter-cell interference. We propose a new direction-based downlink beamforming algorithm for frequency selective TD/CDMA multipath channels. It minimises the radiated array power while suppressing dominant interferers. By considering the directivity of the beam pattern, improved robustness and good spatial filtering properties are achieved. This approach also supports path diversity, assuming that a conventional RAKE is deployed at the mobile. Moreover, it can easily be expanded to facilitate space division multiple access (SDMA).
{"title":"Downlink beamforming for TD/CDMA multipath channels","authors":"M. Schubert, H. Boche","doi":"10.1109/ICASSP.2000.861164","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.861164","url":null,"abstract":"Downlink beamforming has been proposed for high-capacity and spectrally-efficient DS-CDMA wireless systems. It mitigates the effects of multiple access interference, self interference and inter-cell interference. We propose a new direction-based downlink beamforming algorithm for frequency selective TD/CDMA multipath channels. It minimises the radiated array power while suppressing dominant interferers. By considering the directivity of the beam pattern, improved robustness and good spatial filtering properties are achieved. This approach also supports path diversity, assuming that a conventional RAKE is deployed at the mobile. Moreover, it can easily be expanded to facilitate space division multiple access (SDMA).","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131357462","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.861084
T. Davidson
The design of a pulse shaping filter which provides maximal robustness to an unknown frequency-selective channel has previously been formulated as a convex optimization problem from which an optimal filter can be efficiently obtained. Robustness was measured by the worst-case 'peak' intersymbol interference over a class of deterministically bounded channels, and the optimization was subject to a constraint on the bandwidth of the filter. The purpose of the present paper is to show that the design trade-offs between bandwidth, performance in an ideal channel and robustness to unknown channel distortion can be efficiently evaluated using this convex optimization problem. In the design examples, these trade-offs are used to select chip waveforms with superior performance to those specified in standards for digital mobile telephony.
{"title":"Efficient evaluation of trade-offs in waveform design for robust pulse amplitude modulation","authors":"T. Davidson","doi":"10.1109/ICASSP.2000.861084","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.861084","url":null,"abstract":"The design of a pulse shaping filter which provides maximal robustness to an unknown frequency-selective channel has previously been formulated as a convex optimization problem from which an optimal filter can be efficiently obtained. Robustness was measured by the worst-case 'peak' intersymbol interference over a class of deterministically bounded channels, and the optimization was subject to a constraint on the bandwidth of the filter. The purpose of the present paper is to show that the design trade-offs between bandwidth, performance in an ideal channel and robustness to unknown channel distortion can be efficiently evaluated using this convex optimization problem. In the design examples, these trade-offs are used to select chip waveforms with superior performance to those specified in standards for digital mobile telephony.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132390714","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.859247
S. Dockstader, A. Tekalp
Traditional approaches to the estimation of motion in video sequences have relied on the appropriate selection of various algorithm parameters. This dependence becomes a prohibitive drawback in applications where automation is desirable or necessary or in sequences where a single set of parameters can not achieve sufficiently accurate results. We investigate a number of techniques for locally adapting both the spatio-temporal filters and the hierarchical structure used in the estimation of optical flow. The surviving technique utilizes projected active contours and gradient-based Chamfer distance images to adapt the filters and a temporally-based Kolmogorov-Smirnov metric to locally adapt the hierarchical structure. The advantages of using these adaptive variations are demonstrated on articulated and self-occluding motion.
{"title":"Adaptive motion estimation using local measures of texture and similarity","authors":"S. Dockstader, A. Tekalp","doi":"10.1109/ICASSP.2000.859247","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.859247","url":null,"abstract":"Traditional approaches to the estimation of motion in video sequences have relied on the appropriate selection of various algorithm parameters. This dependence becomes a prohibitive drawback in applications where automation is desirable or necessary or in sequences where a single set of parameters can not achieve sufficiently accurate results. We investigate a number of techniques for locally adapting both the spatio-temporal filters and the hierarchical structure used in the estimation of optical flow. The surviving technique utilizes projected active contours and gradient-based Chamfer distance images to adapt the filters and a temporally-based Kolmogorov-Smirnov metric to locally adapt the hierarchical structure. The advantages of using these adaptive variations are demonstrated on articulated and self-occluding motion.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132392540","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.860180
Amy Kraft, R. Green
Traditional short-gate pulse-Doppler devices rely on hardware gating to measure a blood vessel's velocity profile. In the same spirit as software radio, advanced digital signal processor (DSP) technologies suggest software gating as an alternative to traditional hardware gating methods. By way of computer simulation, this paper explores the viability of a software-gated pulse-Doppler technique for measuring a blood vessel's velocity profile. Simulations utilize a particle model that is then mixed, filtered, and sampled. Spectral analysis provides velocity profile information. Preliminary results suggest software gating is not only feasible but, also advantageous.
{"title":"Software-gated pulse-Doppler ultrasound for a DSP-based blood flowmeter","authors":"Amy Kraft, R. Green","doi":"10.1109/ICASSP.2000.860180","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.860180","url":null,"abstract":"Traditional short-gate pulse-Doppler devices rely on hardware gating to measure a blood vessel's velocity profile. In the same spirit as software radio, advanced digital signal processor (DSP) technologies suggest software gating as an alternative to traditional hardware gating methods. By way of computer simulation, this paper explores the viability of a software-gated pulse-Doppler technique for measuring a blood vessel's velocity profile. Simulations utilize a particle model that is then mixed, filtered, and sampled. Spectral analysis provides velocity profile information. Preliminary results suggest software gating is not only feasible but, also advantageous.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130101473","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.860255
P. Sherman
This paper represents the first phase of an ongoing investigation into the nature of sinusoidal types of random processes associated with real world phenomena. Some noteworthy results include the normality of amplitude and frequency, characterization of the same as stationary random processes, and potential to improve condition monitoring of rotating machinery.
{"title":"On the statistical nature of real sinusoids associated with rotating machinery","authors":"P. Sherman","doi":"10.1109/ICASSP.2000.860255","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.860255","url":null,"abstract":"This paper represents the first phase of an ongoing investigation into the nature of sinusoidal types of random processes associated with real world phenomena. Some noteworthy results include the normality of amplitude and frequency, characterization of the same as stationary random processes, and potential to improve condition monitoring of rotating machinery.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130111305","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.861075
Roberto López-Valcarce, S. Dasgupta
We explore the utility of second-order statistics for blind identification/equalization of nonlinear channels. Under standard assumptions it is shown that the channel cannot be identified to within a scaling factor from the output second order statistics, but that the ambiguity is at a level that permits equalization. We show that these results cover cases that the prior literature does not address.
{"title":"Blind channel identifiability/equalizability of single input multiple output nonlinear channels from second order statistics","authors":"Roberto López-Valcarce, S. Dasgupta","doi":"10.1109/ICASSP.2000.861075","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.861075","url":null,"abstract":"We explore the utility of second-order statistics for blind identification/equalization of nonlinear channels. Under standard assumptions it is shown that the channel cannot be identified to within a scaling factor from the output second order statistics, but that the ambiguity is at a level that permits equalization. We show that these results cover cases that the prior literature does not address.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130148316","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.861013
H. Coward, T. Ramstad
The paper proposes a system for combined source-channel coding for transmitting continuous amplitude source symbols on a discrete time, continuous amplitude channel. Two channel symbols are generated for each source symbol. The channel contains additive, white, Gaussian noise, and the measure of quality is the MSE of the reconstructed signal. The coder quantizes the symbols and transmits both the quantized symbol and the quantization error. The quantizer representation values and decision levels are optimized numerically. The results indicate that the use of a uniform quantizer is nearly optimal for a uniformly distributed source. Comparison to another combined source-channel coder designed for a binary channel reveals that the proposed system performs significantly better than the reference systems, more than 5 dB for every channel SNR above 15 dB.
{"title":"Quantizer optimization in hybrid digital-analog transmission of analog source signals","authors":"H. Coward, T. Ramstad","doi":"10.1109/ICASSP.2000.861013","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.861013","url":null,"abstract":"The paper proposes a system for combined source-channel coding for transmitting continuous amplitude source symbols on a discrete time, continuous amplitude channel. Two channel symbols are generated for each source symbol. The channel contains additive, white, Gaussian noise, and the measure of quality is the MSE of the reconstructed signal. The coder quantizes the symbols and transmits both the quantized symbol and the quantization error. The quantizer representation values and decision levels are optimized numerically. The results indicate that the use of a uniform quantizer is nearly optimal for a uniformly distributed source. Comparison to another combined source-channel coder designed for a binary channel reveals that the proposed system performs significantly better than the reference systems, more than 5 dB for every channel SNR above 15 dB.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130167505","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.859316
C. Iordanoglou, K. Jonsson, J. Kittler, Jiri Matas
The feasibility of realising a low cost wearable face recognition aid based on a robust correlation algorithm is investigated. The aim of the study is to determine the limiting spatial and grey level resolution of the probe and gallery images that would support successful prompting of the identity of input face images. Low spatial and grey level resolution images are obtained from good quality image data algorithmically. The tests carried out on the XM2VTS database demonstrate that robust correlation is very resilient to degradations of spatial and grey level image resolution. Correct prompts have been generated in 98% cases even for severely degraded images.
{"title":"Wearable face recognition aid","authors":"C. Iordanoglou, K. Jonsson, J. Kittler, Jiri Matas","doi":"10.1109/ICASSP.2000.859316","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.859316","url":null,"abstract":"The feasibility of realising a low cost wearable face recognition aid based on a robust correlation algorithm is investigated. The aim of the study is to determine the limiting spatial and grey level resolution of the probe and gallery images that would support successful prompting of the identity of input face images. Low spatial and grey level resolution images are obtained from good quality image data algorithmically. The tests carried out on the XM2VTS database demonstrate that robust correlation is very resilient to degradations of spatial and grey level image resolution. Correct prompts have been generated in 98% cases even for severely degraded images.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130185326","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}
Pub Date : 2000-06-05DOI: 10.1109/ICASSP.2000.862046
Yuanjin Zheng, Zhiping Lin
In this paper, the problem of time-varying parametric autoregressive (AR) model identification by wavelets is discussed. Firstly, we derive multiresolution least squares (MLS) algorithm Gaussian time-varying AR model identification employing wavelet operator matrix representation. This method can optimally balance between the over-fitted solution and the poorly represented estimation. Utilizing multiresolution analysis techniques, the smooth trends and the rapidly changing components of time-varying AR model parameters can both be estimated accurately. Then, the proposed MLS algorithm is combined with the total least squares algorithm for noisy time-varying AR model identification. Simulation results verify the effectiveness of our algorithms.
{"title":"Time-varying autoregressive system identification using wavelets","authors":"Yuanjin Zheng, Zhiping Lin","doi":"10.1109/ICASSP.2000.862046","DOIUrl":"https://doi.org/10.1109/ICASSP.2000.862046","url":null,"abstract":"In this paper, the problem of time-varying parametric autoregressive (AR) model identification by wavelets is discussed. Firstly, we derive multiresolution least squares (MLS) algorithm Gaussian time-varying AR model identification employing wavelet operator matrix representation. This method can optimally balance between the over-fitted solution and the poorly represented estimation. Utilizing multiresolution analysis techniques, the smooth trends and the rapidly changing components of time-varying AR model parameters can both be estimated accurately. Then, the proposed MLS algorithm is combined with the total least squares algorithm for noisy time-varying AR model identification. Simulation results verify the effectiveness of our algorithms.","PeriodicalId":164817,"journal":{"name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130186147","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：