Search

Many works have focused on speech emotion recognition algorithms. However, most rely on the proper selection of speech acoustic features. In this paper, we propose a novel emotion recognition algorithm that does not rely on any speech acoustic features and combines speaker gender information. We aim to benefit from the rich information from speech raw data, without any artificial intervention. In general, speech emotion recognition systems require manual selection of appropriate traditional acoustic features as classifier input for emotion recognition. Utilizing deep learning algorithms, and the network automatically select important information from raw speech signal for the classification layer to accomplish emotion recognition. It can prevent the omission of emotion information that cannot be direct mathematically modeled as a speech acoustic characteristic. We also add speaker gender information to the proposed algorithm to further improve recognition accuracy. The proposed algorithm combines a Residual Convolutional Neural Network (R-CNN) and a gender information block. The raw speech data is sent to these two blocks simultaneously. The R-CNN network obtains the necessary emotional information from the speech data and classifies the emotional category. The proposed algorithm is evaluated on three public databases with different language systems. Experimental results show that the proposed algorithm has 5.6%, 7.3%, and 1.5%, respectively accuracy improvements in Mandarin, English, and German compared with existing highest-accuracy algorithms. In order to verify the generalization of the proposed algorithm, we use FAU and eNTERFACE databases, in these two independent databases, the proposed algorithm can also achieve 85.8% and 71.1% accuracy, respectively.

Background and Objectives: To evaluate the effects of low intensity extracorporeal shock wave therapy (LiESWT) on stress urinary incontinence (SUI). Materials and Methods: This investigation was a multicenter, single-blind, randomized-controlled trial study. Sixty female SUI patients were randomly assigned to receive LiESWT with 0.25 mJ/mm2 intensity, 3000 pulses, and 3 pulses/s, once weekly for a 4-week (W4) and 8-week (W8) period, or an identical sham LiESWT treatment without energy transmission. The primary endpoint was the changes in urine leakage as measured by a pad test and validated standardized questionnaires, while the secondary endpoint was the changes in a 3-day urinary diary among the baseline (W0), the W4 and W8 of LiESWT, and 1-month (F1), 3-month (F3), and 6-month (F6) follow-up after LiESWT. Results: The results showed that 4 weeks of LiESWT could significantly decrease urine leakage based on the pad test and validated standardized questionnaire scores, as compared to the sham group. Moreover, 8 weeks of LiESWT could significantly reduce urine leakage but increase urine volume and attenuate urgency symptoms, which showed meaningful and persistent improvement at W8, F1, F3, and F6. Furthermore, validated standardized questionnaire scores were significantly improved at W8, F1, F3, and F6 as compared to the baseline (W0). Conclusions: Eight weeks of LiESWT attenuated SUI symptoms upon physical activity, reduced urine leakage, and ameliorated overactive bladder symptoms, which implied that LiESWT significantly improved the quality of life. Our findings suggested that LiESWT could serve as a potentially novel and non-invasive treatment for SUI.

Background: The present study attempted to investigate the therapeutic effect and duration of low intensity extracorporeal shock wave therapy (LiESWT) on overactive bladder (OAB) symptoms, including social activity and the quality of life (QoL). Methods: In this prospective, randomized, single-blinded clinical trial, 65 participants with OAB symptom were randomly divided into receive LiESWT (0.25 mJ/mm2, 3000 pulses, 3 pulses/second) once a week for 8 weeks, or an identical sham LiESWT treatment without the energy transmission. We analyzed the difference in overactive bladder symptom score (OABSS) and 3-day urinary diary as the primary end. The secondary endpoint consisted of the change in uroflowmetry, post-voided residual (PVR) urine, and validated standardized questionnaires at the baseline (W0), 4-week (W4) and 8-week (W8) of LiESWT, and 1-month (F1), 3-month (F3) and 6-month (F6) follow-up after LiESWT. Results: 8-week LiESWT could significantly decrease urinary frequency, nocturia, urgency, and PVR volume, but meaningfully increase functional bladder capacity, average voided volume and maximal flow rate (Qmax) as compared with the W0 in the LiESWT group. In addition, the scores calculated from questionnaires were meaningfully reduced at W4, W8, F1, F3, and F6 in the LiESWT group. Conclusions: Our results revealed that the therapeutic efficacy of LiESWT could improve voided volume and ameliorate OAB symptoms, such as urgency, frequency, nocturia, and urinary incontinence, and lasted up to 6 month of follow-up. Moreover, LiESWT treatment brought statistically significant and clinically meaningful improvements in social activity and QoL of patients. These findings suggested that LiESWT could serve as an alternative non-invasive therapy for OAB patients.

Nowadays, user identification plays a more and more important role for authorized machine access and remote personal data usage. For reasons of privacy and convenience, biometrics-based user identification, such as iris, fingerprint, and face ID, has become mainstream methods in our daily lives. However, most of the biometric methods can be easily imitated or artificially cracked. New types of biometrics, such as electrocardiography (ECG), are based on physiological signals rather than traditional biological traits. Recently, compressive sensing (CS) technology that combines both sampling and compression has been widely applied to reduce the power of data acquisition and transmission. However, prior CS-based frameworks suffer from high reconstruction overhead and cannot directly align compressed ECG signals. In this paper, in order to solve the above two problems, we propose a compressed alignment-aided compressive analysis (CA-CA) algorithm for ECG-based biometric user identification. With CA-CA, it can avoid reconstruction and extract information directly from CS-based compressed ECG signals to reduce overall complexity and power. Besides, CA-CA can also align the compressed ECG signals in the eigenspace-domain, which can further enhance the precision of identifications and reduce the total training time. The experimental result shows that our proposed algorithm has a 94.16% accuracy based on a public database of 22 people.