The invention discloses a verification system of timing constraint consistency of a Synopsys model and a simulation model. A first format conversion module is used for converting a Synopsys model file into a standard model file. A second format conversion module is used for converting a simulation model file into a standard model file. A comparison verifying module compares timing constraint keywords of the standard model files converted from the Synopsys model file and the simulation model file and outputs a comparison result file containing timing constraint keywords of inconsistency between the standard model files converted from the Synopsys model file and the simulation model file. The invention further discloses a verification method of timing constraint consistency of the Synopsys model and the simulation model. The system and the method allow model design engineers to conveniently verify consistency of timing constraints of the Synopsys model and the simulation model.

Verification system and method of timing constraint consistency of Synopsys model and simulation model

Automatic assessment of dysarthric speech is essential for sustained treatments and rehabilitation. However, obtaining atypical speech is challenging, often leading to data scarcity issues. To tackle the problem, we propose a novel automatic severity assessment method for dysarthric speech, using the self-supervised model in conjunction with multi-task learning. Wav2vec 2.0 XLS-R is jointly trained for two different tasks: severity level classiﬁcation and an auxilary automatic speech recognition (ASR). For the baseline experiments, we employ hand-crafted features such as eGeMaps and linguistic features, and SVM, MLP, and XGBoost classiﬁers. Explored on the Korean dysarthric speech QoLT database, our model outperforms the traditional baseline methods, with a relative percentage increase of 4.79% for classiﬁcation accuracy. In addition, the proposed model surpasses the model trained without ASR head, achieving 10.09% relative percentage improvements. Furthermore, we present how multi-task learning affects the severity classiﬁcation performance by an-alyzing the latent representations and regularization effect.

Automatic Severity Assessment of Dysarthric speech by using Self-supervised Model with Multi-task Learning

A method for determining a sound standard for an input sound signal includes the following steps. Firstly, the input sound signal is filtered to obtain a first filtered signal corresponding to a first frequency and a second filtered signal corresponding to a second frequency. Next, the first filtered signal is frequency-demodulated to obtain a first demodulated filtered signal, and whether the input sound signal contains a FM analog component corresponding to the first frequency is determined accordingly. Next, the second filtered signal is decoded according to a digital sound standard to obtain a bit stream. Then, the bit steam is interpreted according to the digital sound standard, and whether the input sound contains a digital component corresponding to the digital sound standard is determined accordingly. Then, whether the input sound signal matches one of known sound standards is determined based on the determined results above.

Method and apparatus for determining sound standard for input sound signal

In the toxicological testing of new small-molecule compounds, it is desirable to establish in silico test methods to predict toxicity instead of relying on animal testing. Since quantitative structure–activity relationships (QSARs) can predict the biological activity from structural information for small-molecule compounds, QSAR applications for in silico toxicity prediction have been studied for a long time. However, in recent years, the remarkable predictive performance of deep learning has attracted attention for practical applications. In this review, we summarize the application of deep learning to QSAR for constructing prediction models, including a discussion of parameter optimization for deep learning.

/pdf/computational-models-that-use-a-quantitative-structure-3b63zj0k.pdf

Computational Models That Use a Quantitative Structure–Activity Relationship Approach Based on Deep Learning

This paper presents an artificial intelligence based speech signal processing technique to identify dysarthrophonic voice with relative spectral-perceptual linear prediction (RASTA-PLP) features. Dysarthria is a neural motor speech disorder caused by muscular weakness. Voice analysis of dysarthrophonic patients is challenging as this disease has multidimensional effects on the human voice generation system. Conventional spectral analysis is unable to accurately characterize the pathology associated with nonlinear dynamicity of human voice. This work investigates the suitability of RASTA-PLP features excerpted from speech signals to identify dysarthrophonic patients. The speech samples of healthy and dysarthrophonic patients are collected from the Saarbrücken Voice Database (SVD). Several machine learning and Artificial neural network (ANN) based algorithms are developed to evaluate the classification performance of the proposed system. The designed system can achieve excellent performance in terms of accuracy (100%) considering female and male subjects separately. 

Robust Assessment of Dysarthrophonic Voice with RASTA-PLP Features: A Nonlinear Spectral Measures

/pdf/dysarthria-speech-detection-using-convolutional-neural-3sdprj6u.pdf

Dysarthria Speech Detection Using Convolutional Neural Networks with Gated Recurrent Unit

An audio multi-standard detection apparatus is provided to pre-record a plurality of audio broadcasting format carrier bands. The detection apparatus includes: a carrier calculation unit and a switch controller. The carrier calculation unit is used for receiving an intermediate frequency signal and calculates the first carrier energy of the intermediate frequency signal in each of the frequency bands. From this first carrier energy, the switch controller determines which frequency bands are existed in the intermediate frequency signal, then analyzes the signal via at least one threshold value to determine the frequency band's primary carrier. The switch controller obtains an effective carrier. Further, the switch controller compares the effective carrier with the pre-recorded carrier bands for selectively outputting the appropriate audio broadcasting format. Hence, the present invention achieves the objective of determining the appropriate audio multi-standard and enables the support of broadcast systems in various countries with a single audio decoding chip.

Ching-Hsien Liao

Papers

Dysarthria Speech Detection Using Convolutional Neural Networks with Gated Recurrent Unit

Tv audio multi-standard detection apparatus and method

Apparatus and method for determining the transmission standard of a sound transmission transmitted with a television broadcast