Mismatched Conditions Research Articles

Field study on the temperature uniformity of containerized batteries using a two-phase liquid cooling system under mismatched conditions

The conventional liquid cooling system carries the risk of dew condensation and air cooling has poor thermal management performance for battery energy storage systems. To address these issues, a novel two-phase liquid cooling system was developed for containerized battery energy storage systems and tested in the field under mismatched conditions. The thermal management performance and safety during the charging and discharging processes were analyzed by investigating the main influencing factors, including battery temperature and cooling system characteristics (battery temperature variation, temperature uniformity, supply liquid temperature, cold plate temperature distribution, and compressor status). The results showed that the novel system can maintain a maximum cell temperature difference of less than 3°C at the rack level and less than 2°C at the pack level, resulting in a 60% reduction compared to the traditional air cooling system. Relative to a supply liquid temperature of 15∼25°C, a relatively high supply temperature of 20∼30°C for two-phase liquid cooling can not only reduce the running time of the compressor but also enhance its start-stop consistency. Compared to other studies, this novel system is reliable and safe for containerized energy storage batteries, even in capacity mismatch and direct return pipeline conditions.

Dynamic reconfiguration of photovoltaic array for minimizing mismatch loss

Mismatch conditions owing to different internal and external factors, such as partial shading and module defects, can directly degrade the power generation of distributed photovoltaic arrays. In this study, a reconfiguration solution called multiple switching matrices is proposed to mitigate mismatch losses for any size of the total-cross-tied photovoltaic array. In the proposed solution, the photovoltaic array is divided into several sub-arrays using switching matrices. The current and voltage values of each module are collected by the electric measurement sensors and sent to the control unit, and the proposed reconfiguration solution can be implemented by controlling switching matrices. The performance of the proposed reconfiguration solution is evaluated extensively for a range of mismatched conditions, including partial shading patterns and partial shading with random failure patterns. The P–V and I–V characteristics are analyzed by comparison with the existing sudoku-based arrangement and the conventional total-cross-tied interconnection topology. Moreover, three main parameters and standard deviations of the maximum power point for each pattern, are considered. The numerical results confirm the effectiveness and flexibility of the proposed reconfiguration solution for optimizing photovoltaic array generation under various mismatch conditions.

Generalization Ability Improvement of Speaker Representation and Anti-Interference for Speaker Verification

The ability to generalize to mismatches between training and testing conditions and resist interference from other speakers is crucial for the performance of speaker verification. In this paper, we propose two novel approaches to improve the generalization ability to deal with the mismatched recorded scenarios and languages in test conditions and to reduce the influence of interference from other speakers on the similarity measurement of two speaker embeddings. First, parent embedding learning (PEL) is used for model training, which exploits the generalization ability of the shared structure to improve the representation of speaker embeddings. Second, partial adaptive score normalization (PAS-Norm) is used to reduce the influence of interference from other speakers on embedding-based similarity measures. In the experiments, the speaker embedding models are trained using the VoxCeleb2 dataset, and the performance is evaluated on four other datasets under different conditions, including VoxCeleb1, Librispeech, SITW, and CN-Celeb datasets. In the experiments on VoxCeleb1, evaluation results considering a large number of verification speakers and identity restrictions show that the proposed PEL-based system reduces the EER by 6.0% and 4.9% in these two cases, respectively, compared to the state-of-the-art (SOTA) system. Furthermore, in the experiments evaluating speaker verification in mismatch conditions on SITW and CN-Celeb, the proposed PEL-based system also outperforms the SOTA system. In the language mismatched conditions, the EER is reduced by 8.3%. For the evaluation of the influence of interference from other speakers, the EER is significantly reduced by 24.4% when PAS-Norm is used instead of the baseline AS-Norm score normalization method.

The impact of speaking rate on acoustic-to-articulatory inversion

Acoustic characteristics and articulatory movements are known to vary with speaking rates. This study investigates the role of speaking rate on acoustic-to-articulatory inversion (AAI) performance using deep neural networks (DNNs). Since fast speaking rate causes fast articulatory motion as well as changes in spectro-temporal characteristics of the speech signal, the articulatory-acoustic map in a fast speaking rate could be different from that in a slow speaking rate. We examine how these differences alter the accuracy with which different articulatory positions could be recovered from the acoustics. AAI experiments are performed in both matched and mismatched train-test conditions using data of five subjects, in three different rates – normal, fast and slow (fast and slow rates are at least 1.3 times faster and slower than the normal rate). Experiments in matched cases reveal that, the errors in estimating vertical motion of sensors on the tongue articulators from acoustics with fast speaking rate, is significantly higher than those with slow speaking rate. Experiments in mis-matched conditions reveal that there is consistent drop in AAI performance compared to the matched condition. Further experiments performed by training AAI with acoustic-articulatory data pooled from different speaking rates reveal that a single DNN based AAI model is capable of learning multiple rate-specific mapping.

Enhanced Simulated Annealing-based Global MPPT for Different PV Systems in Mismatched Conditions

Enhanced Simulated Annealing-based Global MPPT for Different PV Systems in Mismatched Conditions

An FPGA-Based Advanced Control Strategy of a Grid­Tied PV CHB Inverter

In this paper, an advanced control strategy for grid-tied photovoltaic (PV) cascaded H-bridge (CHB) inverter is proposed. The circuit topology consists of a proper number of power cells (H-bridge configuration) connected in series and supplied by individual PV modules. The adopted control method is a mixed staircase-PWM technique performed by means of a sorting algorithm to determine cells' switching state. The cells' state is related to the need of charging or discharging a particular cell much more than the others by calculating the voltage error at each dc-link (e.g., by considering the difference between the maximum power point tracking (MPPT) reference and the measured quantity). A dedicated P&O MPPT permits to control independently the voltage of each dc-link; thus, increasing the power extraction even in mismatched conditions. In order to prove the effectiveness and feasibility of the proposed approach, a set of experiments are performed on a laboratory prototype of a single-phase five-level PV CHB. The control section is implemented on FPGA by using a dSPACE real-time hardware platform; thus, obtaining fully dedicated digital circuits. Experimental results show good performance in terms of MPPT efficiency, total harmonic distortion, and power factor in both normal operation and mismatch conditions.

Impact of mismatch conditions between mobile phone recordings on forensic voice comparison

Mismatched conditions between the recordings of suspect, offender and relevant background population represent a typical scenario in real forensic casework. In this paper, we investigate the impact of mismatch conditions associated with mobile phone speech recordings on forensic voice comparison (FVC). The two major mobile phone technologies currently in use today are the Global System for Mobile Communications (GSM) and Code Division Multiple Access (CDMA). These are fundamentally different in the way in which they handle the speech signal, which in turn will lead to significant mismatch between speech recordings. Our results suggest that the resulting degradation on the accuracy of a FVC analysis can be very significant (as high as 150%). Surprisingly, though, our results also suggest that the reliability of a FVC analysis may actually improve. We propose a strategy for lessening this impact by passing the suspect speech data through the GSM or CDMA codecs, depending on the network origin of the offender data, prior to the FVC analysis. Though this goes a long way to mitigating the impact (a reduction in loss of accuracy from 150% to 80%), it is still not as good as analysis under matched conditions.

Combining Vocal Tract Length Normalization With Hierarchical Linear Transformations

Recent research has demonstrated the effectiveness of vocal tract length normalization (VTLN) as a rapid adaptation technique for statistical parametric speech synthesis. VTLN produces speech with naturalness preferable to that of MLLR-based adaptation techniques, being much closer in quality to that generated by the original average voice model. However, with only a single parameter, VTLN captures very few speaker specific characteristics when compared to linear transform based adaptation techniques. This paper shows that the merits of VTLN can be combined with those of linear transform based adaptation in a hierarchical Bayesian framework, where VTLN is used as the prior information. A novel technique for propagating the gender and age information captured by the VTLN transform into constrained structural maximum a posteriori linear regression (CSMAPLR) adaptation is presented. This paper also compares this proposed technique to other combination techniques. Experiments are performed on both matched and mismatched training and test conditions, including gender, age, and recording environments. Text-to-speech (TTS) synthesis experiments show that the resulting transformation produces improved speech quality with better naturalness and intelligibility (similar to VTLN transformation) when compared to the CSMAPLR transformation, especially when the quantity of adaptation data is very limited. With more parameters to capture speaker characteristics, the proposed method performs better in speaker similarity compared to VTLN in mis-matched conditions. Hence, the proposed combination combines the quality and intelligibility of VTLN with the speaker similarity of CSMAPLR especially in the mismatched train and test conditions. Experiments are also performed using the automatic speech recognition (ASR) system in a unified framework as that of synthesis. This is to prove that the techniques developed for TTS can be plugged into ASR in order to improve the performance.

Source-Normalized LDA for Robust Speaker Recognition Using i-Vectors From Multiple Speech Sources

The recent development of the i-vector framework for speaker recognition has set a new performance standard in the research field. An i-vector is a compact representation of a speakers utterance extracted from a total variability subspace. Prior to classification using a cosine kernel, i-vectors are projected into an linear discriminant analysis (LDA) space in order to reduce inter-session variability and enhance speaker discrimination. The accurate estimation of this LDA space from a training dataset is crucial to detection performance. A typical training dataset, however, does not consist of utterances acquired through all sources of interest for each speaker. This has the effect of introducing systematic variation related to the speech source in the between-speaker covariance matrix and results in an incomplete representation of the within-speaker scatter matrix used for LDA. The recently proposed source-normalized (SN) LDA algorithm improves the robustness of i-vector-based speaker recognition under both mis-matched evaluation conditions and conditions for which inadequate speech resources are available for suitable system development. When evaluated on the recent NIST 2008 and 2010 Speaker Recognition Evaluations (SRE), SN-LDA demonstrated relative improvements of up to 38% in equal error rate (EER) and 44% in minimum DCF over LDA under mis-matched and sparsely resourced evaluation conditions while also providing improvements in the common telephone-only conditions. Extending on these initial developments, this study provides a thorough analysis of how SN-LDA transforms the i-vector space to reduce source variation and its robustness to varying evaluation and LDA training conditions. The concept of source-normalization is further extended to within-class covariance normalization (WCCN) and data-driven source detection.

Diffusion of collimated, narrow beam waves in discrete random media

The three-dimensional diffusion of a narrow beam wave in discrete random media is discussed. Mismatched boundary conditions are taken into account for surfaces on which the reflection of diffuse light occurs. An analytical expression is derived for the average diffuse intensity in terms of the sum of the residual values under practical situations of interest. The spatial spreading of beam waves for nonabsorption particles only slightly increases with an increase in the mean cosine of the scattering angle. A comparison with previously reported Monte Carlo and experimental results of the beam width versus the optical depth shows the validity of the analytical solutions obtained here. The effects of a mismatched boundary are shown to increase the transmitted diffuse flux rather than the spatial spreading.