Search

This paper proposes a small-footprint wake-up-word (WUW) recognition system for real noisy environments by employing the competing-words-based feature. Competing-words-based features are generated using a ResNet-based deep neural network with small parameters using the competing-words dataset. The competing-words dataset consists of the most acoustically similar and dissimilar words to the WUW used for our system. The obtained features are used as input to the classification network, which is developed using the convolutional neural network (CNN) model. To obtain sufficient data for training, data augmentation is performed by using a room impulse response filter and adding sound signals of various television shows as background noise, which simulates an actual living room environment. The experimental results demonstrate that the proposed WUW recognition system outperforms the baselines that employ CNN and ResNet models. The proposed system shows 1.31% in equal error rate and 1.40% false rejection rate at a 1.0% false alarm rate, which are 29.57% and 50.00% relative improvements compared to the ResNet system, respectively. The number of parameters used for the proposed system is reduced by 83.53% compared to the ResNet system. These results prove that the proposed system with the competing-words-based feature is highly effective at improving WUW recognition performance in noisy environments with a smaller footprint. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate conditional survival among patients with surgically resected stage I-IIIa lung adenocarcinoma and identify changes in prognostic contributions for various prognostic factors over time., Patients and Methods: We performed conditional survival analysis at each t0 (=0, 1, 2, 3, 4, 5 years) for 723 consecutive patients who underwent surgical resection for lung adenocarcinoma, stratified by various clinico-demographic features, as well as pathologic and imaging (tumor-shadow disappearance ratio [TDR] on CT and maximum standardized uptake value [SUVmax] on PET) characteristics. Uni- and multivariableCox regression analyses were performed to evaluate relationships between those variables and conditional survival., Results: Three-year conditional overall survival (OS) and disease-free survival (DFS) were 92.12% and 75.51% at baseline, but improved steadily up to 98.33% and 95.95% at 5 years after surgery. In contrast to demographic factors, pathologic (stage, subtype, pathologic grade and differentiation) and radiologic factors (TDR and SUVmax) maintained a statistically significant association with subseqeunt 3-year OS until 3 years after surgery. According to the multivariableanalysis, high SUVmax and low TDR value were independent predictors of subsequent 3-year OS and DFS at baseline, 1 and 2 years after surgery, respectively., Conclusion: Our findings based on CS provide theoretical background for clinicians to plan longer period of surveillance following lung adenocarcinoma resection in survivors with preoperatively high SUVmax and low TDR on PET-CT and chest CT, respectively.

A new voice activity detector for noisy environments is proposed. In conventional algorithms, the endpoint of speech is found by applying an edge detection filter that finds the abrupt changing point in a feature domain. However, since the frame energy feature is unstable in noisy environments, it is difficult to accurately find the endpoint of speech. Therefore, a novel feature extraction algorithm based on the double-combined Fourier transform and envelope line fitting is proposed. It is combined with an edge detection filter for effective detection of endpoints. Effectiveness of the proposed algorithm is evaluated and compared to other VAD algorithms using two different databases, which are AURORA 2.0 database and SITEC database. Experimental results show that the proposed algorithm performs well under a variety of noisy conditions.