Maxim Vashkevich

Daniil Krasnoproshin, Maxim Vashkevich

Speech emotion recognition is an important component of modern human-computer interaction systems. However, many state-of-the-art approaches rely on large pretrained models with high computational and memory requirements, limiting their applicability. This paper proposes ResLSTM-SA, a lightweight architecture that integrates residual connections with soft attention within an LSTM-based framework. Evaluated on the RAVDESS dataset under strict speaker-independent partitioning, the proposed model outperforms conventional attention-based LSTM baselines and several previously reported CNN- and hybrid CNN-LSTM architectures in terms of unweighted average recall (UAR). The best-performing variant (ResLSTM-SA-h64) achieves a maximum UAR of 0.6517 with only 46.8k trainable parameters, delivering competitive accuracy with three orders of magnitude fewer parameters than large-scale self-supervised alternatives, thereby enabling efficient deployment on edge devices and real-time voice assistants. The source code is available at https://github.com/Mak-Sim/ResLSTM-SER.

Maxim Vashkevich, Egor Krivalcevich

The paper presents a learned two-dimensional separable transform (LST) that can be considered as a new type of computational layer for constructing neural network (NN) architecture for image recognition tasks. The LST based on the idea of sharing the weights of one fullyconnected (FC) layer to process all rows of an image. After that, a second shared FC layer is used to process all columns of image representation obtained from the first layer. The use of LST layers in a NN architecture significantly reduces the number of model parameters compared to models that use stacked FC layers. We show that a NN-classifier based on a single LST layer followed by an FC layer achieves 98.02\% accuracy on the MNIST dataset, while having only 9.5k parameters. We also implemented a LST-based classifier for handwritten digit recognition on the FPGA platform to demonstrate the efficiency of the suggested approach for designing a compact and high-performance implementation of NN models. Git repository with supplementary materials: https://github.com/Mak-Sim/LST-2d

Maxim Vashkevich, Yulia Rushkevich

Amyotrophic lateral sclerosis (ALS) is incurable neurological disorder with rapidly progressive course. Common early symptoms of ALS are difficulty in swallowing and speech. However, early acoustic manifestation of speech and voice symptoms is very variable, that making their detection very challenging, both by human specialists and automatic systems. This study presents an approach to voice assessment for automatic system that separates healthy people from patients with ALS. In particular, this work focus on analysing of sustain phonation of vowels /a/ and /i/ to perform automatic classification of ALS patients. A wide range of acoustic features such as MFCC, formants, jitter, shimmer, vibrato, PPE, GNE, HNR, etc. were analysed. We also proposed a new set of acoustic features for characterizing harmonic structure of the vowels. Calculation of these features is based on pitch synchronized voice analysis. A linear discriminant analysis (LDA) was used to classify the phonation produced by patients with ALS and those by healthy individuals. Several algorithms of feature selection were tested to find optimal feature subset for LDA model. The study's experiments show that the most successful LDA model based on 32 features picked out by LASSO feature selection algorithm attains 99.7% accuracy with 99.3% sensitivity and 99.9% specificity. Among the classifiers with a small number of features, we can highlight LDA model with 5 features, which has 89.0% accuracy (87.5% sensitivity and 90.4% specificity).

Maxim Vashkevich, Alexander Petrovsky, Yuliya Rushkevich

On average the lack of biological markers causes a one year diagnostic delay to detect amyotrophic lateral sclerosis (ALS). To improve the diagnostic process an automatic voice assessment based on acoustic analysis can be used. The purpose of this work was to verify the sutability of the sustain vowel phonation test for automatic detection of patients with ALS. We proposed enhanced procedure for separation of voice signal into fundamental periods that requires for calculation of perturbation measurements (such as jitter and shimmer). Also we proposed method for quantitative assessment of pathological vibrato manifestations in sustain vowel phonation. The study's experiments show that using the proposed acoustic analysis methods, the classifier based on linear discriminant analysis attains 90.7\% accuracy with 86.7\% sensitivity and 92.2\% specificity.