Audio event classification refers to the detection and classification of non-verbal signals, such as dog and horn sounds included in audio data, by a computer. Recently, deep neural network technology has been applied to audio event classification, exhibiting higher performance when compared to existing models. Among them, a convolutional neural network (CNN)-based training method that receives audio in the form of a spectrogram, which is a two-dimensional image, has been widely used. However, audio event classification has poor performance on test data when it is recorded by a device (unknown device) different from that used to record training data (known device). This is because the frequency range emphasized is different for each device used during recording, and the shapes of the resulting spectrograms generated by known devices and those generated by unknown devices differ. In this study, to improve the performance of the event classification system, a CNN based on the log mel-spectrogram separation technique was applied to the event classification system, and the performance of unknown devices was evaluated. The system can classify 16 types of audio signals. It receives audio data at 0.4-s length, and measures the accuracy of test data generated from unknown devices with a model trained via training data generated from known devices. The experiment showed that the performance compared to the baseline exhibited a relative improvement of up to 37.33%, from 63.63% to 73.33% based on Google Pixel, and from 47.42% to 65.12% based on the LG V50.

In this study, an automatic end-to-end speech recognition system based on hybrid CTC-attention network for Korean language is proposed. Deep neural network/hidden Markov model (DNN/HMM)-based speech recognition system has driven dramatic improvement in this area. However, it is difficult for non-experts to develop speech recognition for new applications. End-to-end approaches have simplified speech recognition system into a single-network architecture. These approaches can develop speech recognition system that does not require expert knowledge. In this paper, we propose hybrid CTC-attention network as end-to-end speech recognition model for Korean language. This model effectively utilizes a CTC objective function during attention model training. This approach improves the performance in terms of speech recognition accuracy as well as training speed. In most languages, end-to-end speech recognition uses characters as output labels. However, for Korean, character-based end-to-end speech recognition is not an efficient approach because Korean language has 11,172 possible numbers of characters. The number is relatively large compared to other languages. For example, English has 26 characters, and Japanese has 50 characters. To address this problem, we utilize Korean 49 graphemes as output labels. Experimental result shows 10.02% character error rate (CER) when 740 hours of Korean training data are used.

One of the most important parts of a text-independent speaker verification system is speaker embedding generation. Previous studies demonstrated that shortcut connections-based multi-layer aggregation improves the representational power of a speaker embedding system. However, model parameters are relatively large in number, and unspecified variations increase in the multi-layer aggregation. Therefore, in this study, we propose a self-attentive multi-layer aggregation with feature recalibration and deep length normalization for a text-independent speaker verification system. To reduce the number of model parameters, we set the ResNet with the scaled channel width and layer depth as a baseline. To control the variability in the training, we apply a self-attention mechanism to perform multi-layer aggregation with dropout regularizations and batch normalizations. Subsequently, we apply a feature recalibration layer to the aggregated feature using fully-connected layers and nonlinear activation functions. Further, deep length normalization is used on a recalibrated feature in the training process. Experimental results using the VoxCeleb1 evaluation dataset showed that the performance of the proposed methods was comparable to that of state-of-the-art models (equal error rate of 4.95% and 2.86%, using the VoxCeleb1 and VoxCeleb2 training datasets, respectively).

KSII Transactions on Internet and Information Systems TIIS Paper Details

Acoustic scene classification (ASC) is a method of recognizing and classifying environments that employ acoustic signals. Various ASC approaches based on deep learning have been developed, with convolutional neural networks (CNNs) proving to be the most reliable and commonly utilized in ASC systems due to their suitability for constructing lightweight models. When using ASC systems in the real world, model complexity and device robustness are essential considerations. In this paper, we propose a two-pass mobile network for low-complexity classification of the acoustic scene, named TP-MobNet. With inverse residuals and linear bottlenecks, TP-MobNet is based on MobileNetV2, and following mobile blocks, coordinate attention and two-pass fusion approaches are utilized. The log-range dependencies and precise position information in feature maps can be trained via coordinate attention. By capturing more diverse feature resolutions at the network's end sides, two-pass fusions can also train generalization. Also, the model size is reduced by applying weight quantization to the trained model. By adding weight quantization to the trained model, the model size is also lowered. The TAU Urban Acoustic Scenes 2020 Mobile development set was used for all of the experiments. It has been confirmed that the proposed model, with a model size of 219.6 kB, achieves an accuracy of 73.94%.

In general, a self-attention mechanism has been applied for speaker embedding encoding. Previous studies focused on training the self-attention in a high-level layer, such as the last pooling layer. However, the effect of low-level features was reduced in the speaker embedding encoding. Therefore, we propose masked cross self-attentive encoding (MCSAE) using ResNet. It focuses on the features of both high-level and lowlevel layers. Based on multi-layer aggregation, the output features of each residual layer are used for the MCSAE. In the MCSAE, cross self-attention module is trained the interdependence of each input features. A random masking regularization module also applied to preventing overfitting problem. As such, the MCSAE enhances the weight of frames representing the speaker information. Then, the output features are concatenated and encoded to the speaker embedding. Therefore, a more informative speaker embedding is encoded by using the MCSAE. The experimental results showed an equal error rate of 2.63% and a minimum detection cost function of 0.1453 using the VoxCeleb1 evaluation dataset. These were improved performances compared with the previous self-attentive encoding and state-of-the-art encoding methods.