The Experts below are selected from a list of 79824 Experts worldwide ranked by ideXlab platform
Juinhwey Chen - One of the best experts on this subject based on the ideXlab platform.
-
Packet Loss concealment based on extrapolation of speech waveform
International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Juinhwey ChenAbstract:A class of Packet Loss concealment algorithms for speech coding is presented. It generates the replacement waveform for the lost frame by direct extrapolation of the past speech waveform, with or without look-ahead. The ITU-T G.722 Appendix III standard is based on it. When a future frame is unavailable (without look-ahead), the PLC algorithm gives significantly better speech quality than G.711 Appendix I - by about 0.2 PESQ for high Packet Loss rates. When a future frame is available (with look-ahead), the PLC algorithm uses the decoded speech waveform in the future frame to guide the pitch contour of waveform extrapolation during the lost frame such that the extrapolated waveform is phase-aligned with the decoded waveform after the Packet Loss. This technique further improved PESQ by another 0.2 for high Packet Loss rates.
-
ICASSP - Packet Loss concealment based on extrapolation of speech waveform
2009 IEEE International Conference on Acoustics Speech and Signal Processing, 2009Co-Authors: Juinhwey ChenAbstract:A class of Packet Loss concealment algorithms for speech coding is presented. It generates the replacement waveform for the lost frame by direct extrapolation of the past speech waveform, with or without look-ahead. The ITU-T G.722 Appendix III standard is based on it. When a future frame is unavailable (without look-ahead), the PLC algorithm gives significantly better speech quality than G.711 Appendix I - by about 0.2 PESQ for high Packet Loss rates. When a future frame is available (with look-ahead), the PLC algorithm uses the decoded speech waveform in the future frame to guide the pitch contour of waveform extrapolation during the lost frame such that the extrapolated waveform is phase-aligned with the decoded waveform after the Packet Loss. This technique further improved PESQ by another 0.2 for high Packet Loss rates.
Ben Milner - One of the best experts on this subject based on the ideXlab platform.
-
Towards improving the robustness of distributed speech recognition in Packet Loss
Speech Communication, 2006Co-Authors: Alastair Bruce James, Ben MilnerAbstract:This work addresses the problem of achieving robust distributed speech recognition (DSR) performance in the presence of Packet Loss. The nature of Packet Loss is analysed by examining Packet Loss data gathered from a GSM mobile data channel. This analysis is then used to examine the effect of realistic Packet Loss conditions on DSR systems, and shows that the accuracy of DSR is more sensitive to burst-like Packet Loss rather than the actual number of lost Packets. This leads to the design of a three-stage Packet Loss compensation scheme. First, interleaving is applied to the transmitted feature vectors to disperse bursts of Packet Loss. Second, lost feature vectors are reconstructed prior to recognition using a variety of reconstruction techniques. Third, a weighted-Viterbi decoding method is applied to the recogniser itself, which modifies the contribution of the reconstructed feature vectors according to the accuracy of their reconstruction. Experimental results on both a connected digits task and a large-vocabulary task show that simple methods, such as repetition, are not as effective as interpolation methods. Best performance is given by a novel maximum a posteriori (MAP) estimation, which utilizes temporal statistics of the feature vector stream. This reconstruction method is then combined with weighted-Viterbi decoding, using a novel method to calculate the confidences of reconstructed static and temporal components separately. Using interleaving, results improve significantly, and it is shown that a limited level of interleaving can be applied without increasing the delay to the end-user. Using a combination of these techniques for the connected digits task, word accuracy is increased from 49.5% to 95.3% even with a Packet Loss rate of 50% and average burst length of 20 feature vectors.
-
INTERSPEECH - A comparison of Packet Loss compensation methods and interleaving for speech recognition in burst-like Packet Loss.
2004Co-Authors: Alastair Bruce James, Ben Milner, A. M. GomazAbstract:This work compares the performance of three compensation methods for speech recognition in the presence of Packet Loss. Two methods, cubic interpolation and a novel maximum a posteriori (MAP) estimation, aim to restore the feature vector stream in the event of Packet Loss, while the third technique applies compensation in the decoding stage of recognition through missing feature theory. To improve performance in burst-like Packet Loss, interleaving is introduced to disperse bursts of Loss. Experiments on the ETSI Aurora connected digit task show best performance to be given by a combination of missing feature theory and cubic interpolation. This raises performance from 50.3% to 69.8% at a Packet Loss rate of 50% and average burst length of 20 Packets. Including interleaving further increases performance to over 76%.
-
Packet Loss Modelling for Distributed Speech Recognition
2004Co-Authors: Ben Milner, Alastair Bruce JamesAbstract:The evaluation of Packet Loss compensation techniques for distributed speech recognition requires an effective model of Packet Loss that is capable of reproducing the burst-like occurrence of Loss. Several models have been applied to this task and are based on two or three state Markov chains or Markov models. This work reviews these models in terms of their channel characteristics such as the probability of Packet Loss and average burst length. Validation of the models is made against both GSM error patterns and a wireless LAN channel which demonstrates effective simulation. A series of speech recognition tests show that similar performance is obtained on the real and simulated channels using the Packet Loss models. Finally a set of model parameters is presented which allows testing across a range of channel conditions.
-
ICASSP - Robust speech recognition in burst-like Packet Loss
2001 IEEE International Conference on Acoustics Speech and Signal Processing. Proceedings (Cat. No.01CH37221), 1Co-Authors: Ben MilnerAbstract:This paper examines problems associated with performing speech recognition over mobile and IP networks. The main problems are identified as codec-based distortion and from speech vectors being lost from Packet Loss in the network. A realistic model for Packet Loss is developed, based on a three state Markov model and is shown to be capable of simulating the burst-like nature of Packet Loss. A two stage Packet Loss detection and estimation scheme is proposed and is shown to improve the recognition performance in the event of feature vectors being lost. Results from the Aurora database show that burst-like Packet Loss reduces the digit accuracy from 99% to 57% at 50% Packet Loss. Estimation of the lost Packets recovers the performance to 77%.
Tutomu Murase - One of the best experts on this subject based on the ideXlab platform.
-
estimating tcp Packet Loss ratio from sampled ack Packets
IEICE Transactions on Communications, 2008Co-Authors: Yasuhiro Yamasaki, Hideyuki Shimonishi, Tutomu MuraseAbstract:The advent of various quality-sensitive applications has greatly changed the requirements for IP network management and made the monitoring of individual traffic flows more important. Since the processing costs of per-flow quality monitoring are high, especially in high-speed backbone links, Packet sampling techniques have been attracting considerable attention. Existing sampling techniques, such as those used in Sampled NetFlow and sFlow, however, focus on the monitoring of traffic volume, and there has been little discussion of the monitoring of such quality indexes as Packet Loss ratio. In this paper we propose a method for estimating, from sampled Packets, Packet Loss ratios in individual TCP sessions. It detects Packet Loss events by monitoring duplicate ACK events raised by each TCP receiver. Because sampling reveals only a portion of the actual Packet Loss, the actual Packet Loss ratio is estimated statistically. Simulation results show that the proposed method can estimate the TCP Packet Loss ratio accurately from a 10% sampling of Packets.
-
statistical estimation of tcp Packet Loss rate from sampled ack Packets
Global Communications Conference, 2005Co-Authors: Yasuhiro Yamasaki, Hideyuki Shimonishi, Tutomu MuraseAbstract:The appearance of various quality-sensitive applications has greatly changed the requirements for network management. To manage the quality of these applications, monitoring of individual traffic flows, as well as aggregated traffic statistics, has become more important. Since per-flow monitoring involves a high processing cost, especially in emerging high-speed links, Packet sampling techniques have been attracting considerable attention. However, existing sampling techniques, such as NetFlow and sFlow, have mainly targeted traffic volume monitoring and there has been little discussion on the monitoring of quality indexes including Packet Loss rate. In this paper, we propose a method to estimate the TCP Packet Loss rate from sampled Packets. The proposed method detects Packet Loss events by monitoring duplicate ACK events induced by a TCP receiver indicating the Loss events. Since only a portion of Packet Loss events can be detected from the sampled Packets, the correct Packet Loss rate is estimated by means of statistical approximation. Simulation results show that the proposed method accurately estimates the TCP Packet Loss rate from 10% of sampled Packets.
-
GLOBECOM - Statistical estimation of TCP Packet Loss rate from sampled ACK Packets
GLOBECOM '05. IEEE Global Telecommunications Conference 2005., 2005Co-Authors: Yasuhiro Yamasaki, Hideyuki Shimonishi, Tutomu MuraseAbstract:The appearance of various quality-sensitive applications has greatly changed the requirements for network management. To manage the quality of these applications, monitoring of individual traffic flows, as well as aggregated traffic statistics, has become more important. Since per-flow monitoring involves a high processing cost, especially in emerging high-speed links, Packet sampling techniques have been attracting considerable attention. However, existing sampling techniques, such as NetFlow and sFlow, have mainly targeted traffic volume monitoring and there has been little discussion on the monitoring of quality indexes including Packet Loss rate. In this paper, we propose a method to estimate the TCP Packet Loss rate from sampled Packets. The proposed method detects Packet Loss events by monitoring duplicate ACK events induced by a TCP receiver indicating the Loss events. Since only a portion of Packet Loss events can be detected from the sampled Packets, the correct Packet Loss rate is estimated by means of statistical approximation. Simulation results show that the proposed method accurately estimates the TCP Packet Loss rate from 10% of sampled Packets.
Zibao Lu - One of the best experts on this subject based on the ideXlab platform.
-
A Switching Approach to Packet Loss Compensation Strategy
IEEE Access, 2019Co-Authors: Zibao Lu, Shangpeng Zhong, Liguo QuAbstract:In networked control systems, a zero or hold compensation strategy is usually used for the missing signal when a Packet is lost. In this paper, a switching approach is proposed for the consecutive Loss compensation, where the Packet Loss between sensor and controller is modeled as an i.i.d. Bernoulli process. The held signal was divided into three categories, that is, the current signal, usable signal, and unusable signal, according to the number of consecutive Loss. Then, the system is built as a switching system with normal, time-delay, and open-loop subsystems, where the switching rule associates with the Packet Loss. It is theoretically proved that the proposed switching approach is effective for Packet Loss compensation. The dividing criteria of the held sensor measurements are derived. The usefulness of the proposed results is verified by a numerical example.
-
CDC - An improved hold strategy to Packet Loss compensation
2017 IEEE 56th Annual Conference on Decision and Control (CDC), 2017Co-Authors: Zibao LuAbstract:This paper investigates networked control systems subjected to Packet Loss over the channel between actuator and controller. The Packet Loss is modeled as an i.i.d. Bernoulli process. An improved held compensation strategy is proposed for the consecutive Packet Loss. Based on the fact that the past signal held multi-step in a buffer is too old to be suitable for the current calculation, we delete the too old held signal. A switching approach is used to describe the dynamics of the held sensor measurements, where the switching rule associates with the Packet Loss. A hold-based stability analysis and controller design framework dependent on the Packet Loss probability is established. A numerical example has shown the usefulness of the proposed results.
Alastair Bruce James - One of the best experts on this subject based on the ideXlab platform.
-
Towards improving the robustness of distributed speech recognition in Packet Loss
Speech Communication, 2006Co-Authors: Alastair Bruce James, Ben MilnerAbstract:This work addresses the problem of achieving robust distributed speech recognition (DSR) performance in the presence of Packet Loss. The nature of Packet Loss is analysed by examining Packet Loss data gathered from a GSM mobile data channel. This analysis is then used to examine the effect of realistic Packet Loss conditions on DSR systems, and shows that the accuracy of DSR is more sensitive to burst-like Packet Loss rather than the actual number of lost Packets. This leads to the design of a three-stage Packet Loss compensation scheme. First, interleaving is applied to the transmitted feature vectors to disperse bursts of Packet Loss. Second, lost feature vectors are reconstructed prior to recognition using a variety of reconstruction techniques. Third, a weighted-Viterbi decoding method is applied to the recogniser itself, which modifies the contribution of the reconstructed feature vectors according to the accuracy of their reconstruction. Experimental results on both a connected digits task and a large-vocabulary task show that simple methods, such as repetition, are not as effective as interpolation methods. Best performance is given by a novel maximum a posteriori (MAP) estimation, which utilizes temporal statistics of the feature vector stream. This reconstruction method is then combined with weighted-Viterbi decoding, using a novel method to calculate the confidences of reconstructed static and temporal components separately. Using interleaving, results improve significantly, and it is shown that a limited level of interleaving can be applied without increasing the delay to the end-user. Using a combination of these techniques for the connected digits task, word accuracy is increased from 49.5% to 95.3% even with a Packet Loss rate of 50% and average burst length of 20 feature vectors.
-
INTERSPEECH - A comparison of Packet Loss compensation methods and interleaving for speech recognition in burst-like Packet Loss.
2004Co-Authors: Alastair Bruce James, Ben Milner, A. M. GomazAbstract:This work compares the performance of three compensation methods for speech recognition in the presence of Packet Loss. Two methods, cubic interpolation and a novel maximum a posteriori (MAP) estimation, aim to restore the feature vector stream in the event of Packet Loss, while the third technique applies compensation in the decoding stage of recognition through missing feature theory. To improve performance in burst-like Packet Loss, interleaving is introduced to disperse bursts of Loss. Experiments on the ETSI Aurora connected digit task show best performance to be given by a combination of missing feature theory and cubic interpolation. This raises performance from 50.3% to 69.8% at a Packet Loss rate of 50% and average burst length of 20 Packets. Including interleaving further increases performance to over 76%.
-
Packet Loss Modelling for Distributed Speech Recognition
2004Co-Authors: Ben Milner, Alastair Bruce JamesAbstract:The evaluation of Packet Loss compensation techniques for distributed speech recognition requires an effective model of Packet Loss that is capable of reproducing the burst-like occurrence of Loss. Several models have been applied to this task and are based on two or three state Markov chains or Markov models. This work reviews these models in terms of their channel characteristics such as the probability of Packet Loss and average burst length. Validation of the models is made against both GSM error patterns and a wireless LAN channel which demonstrates effective simulation. A series of speech recognition tests show that similar performance is obtained on the real and simulated channels using the Packet Loss models. Finally a set of model parameters is presented which allows testing across a range of channel conditions.
