{"title":"An extension to Fisher Linear Semi-Discriminant analysis for Speaker Diarization","authors":"S. Montazzolli, Andre Gustavo Adami, D. Barone","doi":"10.1109/ITS.2014.6947969","DOIUrl":"https://doi.org/10.1109/ITS.2014.6947969","url":null,"abstract":"The Fisher Linear Semi-Discriminant Analysis is used in Speaker Diarization to project acoustic features into a discriminant and lower dimensional space. Given that such analysis uses short segments to estimate the scatter matrices, the projection could be improved by using longer segments (i.e., more information). Since a change of speaker is more likely to occur during periods of non-speech, we propose to use segments of speech produced by the boundaries estimated from a voice activity detection method based on Hidden Markov Models. Using datasets from the NIST Speaker Recognition Evaluations, we show that the estimated segments provide a better scatter matrices for the analysis. The results show a relative improvement of 21% in the Speaker Error Time on the Switchboard corpus used in the evaluations.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129182318","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}
{"title":"PNCC features and FNN - MAP compensation techniques for continuous speech recognition","authors":"Christian Arcos Gordillo, M. Grivet, A. Alcaim","doi":"10.1109/ITS.2014.6948038","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948038","url":null,"abstract":"One of the biggest problems of a speech recognition system is the signal degradation due to adverse conditions. Such situations usually lead to mismatch between the test conditions and the training data, caused by non-linear distortion. The authors propose a histogram mapping followed by a filter through neural networks techniques (based on the features compensation), in order to minimize the misfit caused by noise insertion in the speech signal. The proposed method has been evaluated using the TIMIT and Noisex-92 databases. Recognition results show that the histogram mapping combined with filter with neural networks in the field of the cepstral coefficients do improve the recognition rates.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130503732","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}
Luiz Carlos Branquinho Ferreira, P. Cardieri, Omar Carvalho Branquinho, Thiago Tortorelli de Faria
{"title":"Geographic routing by using location algorithm based in signal measurements","authors":"Luiz Carlos Branquinho Ferreira, P. Cardieri, Omar Carvalho Branquinho, Thiago Tortorelli de Faria","doi":"10.1109/ITS.2014.6948002","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948002","url":null,"abstract":"This work proposes a geographic routing for wireless sensor networks, where the position of the sensor nodes is found through the use of a location algorithm based on RSSI values. The goal is that the proposed protocol creates a sensor network map by analyzing the conditions of the work environment, since the RSSI values are directly affected by the conditions that act on the radio signal. The protocol was simulated, implemented in a real WSN and its functionality was evaluated and compared with another existing technique in the literature.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131925410","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}
{"title":"High data rate acoustic modem for underwater aplications","authors":"M. Martins, N. Pinto, J. Carmo, J. Cabral","doi":"10.1109/ITS.2014.6948005","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948005","url":null,"abstract":"The development of an underwater wireless communication systems is becoming a research and a technological priority due to the increasing demand for exploring the potential of oceans in fields such as pharmaceutics, oil, minerals, environmental and biodiversity. However, underwater wireless communications still fail to ensure high data-rate connections which support real time applications. In this work a low power high data-rate acoustic modem is presented, based on a piezoelectric poly (vinylidene fluoride) polymer as a transducer and a Xilinx Field Programmable Gate Array (FPGA) that can be programmed to work with different types of modulations. The system has been validated by the implementation of a full duplex point-to-point communication at 1 Mbps using On-Off Keying (OOK) modulation with a 1 MHz single carrier and it represents a major advance in the state of the art and a breakthrough in underwater acoustic communications, being the first to show the possibility to achieve data rates up to 1Mbps. It was successfully tested with a 1 Mbps rate, achieving a 3×10-3 Bit Error Rate (BER) using just 1.4 μW of power consumption per bit.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129160236","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}
{"title":"PAPR and saturation effects of power amplifiers in SM OFDM and V-BLAST OFDM systems","authors":"J. Jacob, C. Panazio, T. Abrão","doi":"10.1109/ITS.2014.6948031","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948031","url":null,"abstract":"The paper firstly analyzes the complementary cumulative distribution function (CCDF) of the peak-to-average power ratio (PAPR) of the spatial modulation (SM) and vertical Bell Labs layered space-time (V-BLAST) transmission schemes, with both systems using the orthogonal frequency division multiplexing (OFDM). In a second step, for specific values of input back-off (IBO), we investigate the clipping effect of a hard-limiter high power amplifier (HPA) on the bit error rate (BER) performance of both systems. Moreover, for a fair comparison, the maximum likelihood (ML) detector is used in both OFDM systems. Multipath Rayleigh fading channels and uncoded signals have been considered. Simulation results show that the SM OFDM, for a large number of subcarriers, presents practically the same PAPR behavior of the V-BLAST OFDM system. On the other hand, for a small number of subcarriers, a large number of antennas and higher-order modulations it seldom attains higher PAPR values than V-BLAST OFDM, which does not implies in practical performance degradation. However, in terms of BER, it turns out that the SM OFDM system is much more sensitive to the ICI generated by clipping resultant of the HPA when its modulation cardinality is higher than the one used in the V-BLAST OFDM system.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115141019","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}
Celio K. H. Vasconcelos, A. Barreto, D. Mello, F. Simões
{"title":"Signal predistortion for nonlinear transmitters in direct-detection OFDM over multimode fibers","authors":"Celio K. H. Vasconcelos, A. Barreto, D. Mello, F. Simões","doi":"10.1109/ITS.2014.6948043","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948043","url":null,"abstract":"This paper investigates the transmission of OFDM signals, generated by a directly-modulated VCSEL, over an optical channel estimated from experimental measurements in OM-3 multimode fibers. Simulation results indicate limitations on the system performance due to the nonlinear L-I curve of the VCSEL. We show that, in these conditions, the system performance can be improved by transmitter predistortion.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114693877","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}
{"title":"Power-rate control in multirate multiple access networks via heuristic ant colony optimization","authors":"Mateus de Paula Marques, F. Ciriaco, T. Abrão","doi":"10.1109/ITS.2014.6948039","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948039","url":null,"abstract":"In this paper, continuous heuristic ant colony optimization (ACOℝ) [11] procedure is deployed to solve the powerrate optimization problem in multirate multi-processing gain (MPG) DS/CDMA networks. The power-rate allocation design is formulated as a special case of generalized linear fractional problem (GLFP), allowing the multiple access system to operate under best power-rate trade-off operation point. Numerical results considering realistic wireless mobile channels and system operation conditions have been shown the applicability of the ACOR heuristic approach in order to solve this hard problem with practical interest in real energy-efficient, spectral-efficient CDMA systems, as well as of paramount interest in establishing the next wireless generation green communication networks.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131469910","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}
C. Vázquez, A. Hadarig, S. Ver Hoeye, Miguel Fernández, R. Camblor, G. Hotopan, F. Las-Heras
{"title":"Millimetre wave subharmonic mixer based on graphene","authors":"C. Vázquez, A. Hadarig, S. Ver Hoeye, Miguel Fernández, R. Camblor, G. Hotopan, F. Las-Heras","doi":"10.1109/ITS.2014.6948016","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948016","url":null,"abstract":"An eighth order subharmonically pumped mixer for the implementation of a millimetre wave imaging system is presented. The block receives the RF signal in the WR-3 band, between 220 and 330 GHz, and downconverts it to a 300 MHz intermediate frequency, using the internally generated eighth harmonic component of an input signal in the WR-28 frequency band, between 26.5 and 40 GHz. The subharmonic mixing operation is performed taking advantage of the non-linearity of a few layer graphene component, integrated in a microstrip structure.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125496076","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}
Marcelo de Campos Niero, Alvaro de Lima Veiga Filho, Andre Gustavo Adami
{"title":"A comparison of distance measures for clustering in speaker diarization","authors":"Marcelo de Campos Niero, Alvaro de Lima Veiga Filho, Andre Gustavo Adami","doi":"10.1109/ITS.2014.6947954","DOIUrl":"https://doi.org/10.1109/ITS.2014.6947954","url":null,"abstract":"Speaker diarization consists in answering the question “Who spoke when” for a given conversation in a telephone call, meeting, or broadcast news, without any prior information about neither the audio nor the speakers. Speaker diarization task emerged as a way to optimize audio information retrieval processing by detecting and tracking speech and speaker information. Computationally speaking, the diarization processing occurs through four main steps: feature extraction of signal, speech and non-speech detection, segmentation and clustering. In this work, the clustering step is analyzed by comparing distance measures commonly used in current speaker diarization systems. The results show that pairs of clusters with a large difference in the number of data samples are more sensitive to errors, the number of mixtures of an external model affects the discriminative power of distance measures, and the number of estimated parameters affects the speaker discrimination. All experiments are performed on an excerpt from TIMIT corpus and the diarization task database used in the 2002 NIST Speaker Recognition Evaluation.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115077806","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}
{"title":"Performance evaluation of MPTCP over optical burst switching in data centers","authors":"S. Tariq, M. Bassiouni","doi":"10.1109/ITS.2014.6948036","DOIUrl":"https://doi.org/10.1109/ITS.2014.6948036","url":null,"abstract":"Data centers have become the heart of the computational world over the past few years. The emergence of cloud computing and the growth of data-intensive applications have driven the need for finding alternative ways to improve communication efficiency in data center networks. In this paper, we combine the advantages of Multipath-TCP with optical networking to maximize bandwidth in datacenters and present an evaluation of MPTCP over optical burst switching (OBS) for data center network. We compare the performance of standard TCP with MPTCP under different network loads and topologies using realistic data center traffic models. Our simulation tests have established that Multipath-TCP over OBS provides significant performance advantage in terms of improving throughput, reliability and fairness for data center networks.","PeriodicalId":359348,"journal":{"name":"2014 International Telecommunications Symposium (ITS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130088561","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}