arXiv subjects

Yong-Hwa Park

Publications and source records attributed to Yong-Hwa Park.

30 records · Page 2Linked to original sources

arXiv2023

Automatic Internal Stray Light Calibration of AMCW Coaxial Scanning LiDAR Using GMM and PSO

In this paper, an automatic calibration algorithm is proposed to reduce the depth error caused by internal stray light in amplitude-modulated continuous wave (AMCW) coaxial scanning light detection and ranging (LiDAR). Assuming that the internal stray light generated in the process of emitting laser is static, the amplitude and phase delay of internal stray light are estimated using the Gaussian mixture model (GMM) and particle swarm optimization (PSO). Specifically, the pixel positions in a raw signal amplitude map of calibration checkboard are segmented by GMM with two clusters considering the dark and bright image pattern. The loss function is then defined as L1-norm of difference between mean depths of two amplitude-segmented clusters. To avoid overfitting at a specific distance in PSO process, the calibration check board is actually measured at multiple distances and the average of corresponding L1 loss functions is chosen as the actual loss. Such loss is minimized by PSO to find the two optimal target parameters: the amplitude and phase delay of internal stray light. According to the validation of the proposed algorithm, the original loss is reduced from tens of centimeters to 3.2 mm when the measured distances of the calibration checkboard are between 1 m and 4 m. This accurate calibration performance is also maintained in geometrically complex measured scene. The proposed internal stray light calibration algorithm in this paper can be used for any type of AMCW coaxial scanning LiDAR regardless of its optical characteristics.

eess.IV↗

arXiv2022

Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation Map

To extract accurate speaker information for text-independent speaker verification, temporal dynamic CNNs (TDY-CNNs) adapting kernels to each time bin was proposed. However, model size of TDY-CNN is too large and the adaptive kernel's degree of freedom is limited. To address these limitations, we propose decomposed temporal dynamic CNNs (DTDY-CNNs) which forms time-adaptive kernel by combining static kernel with dynamic residual based on matrix decomposition. Proposed DTDY-ResNet-34(x0.50) using attentive statistical pooling without data augmentation shows EER of 0.96%, which is better than other state-of-the-art methods. DTDY-CNNs are successful upgrade of TDY-CNNs, reducing the model size by 64% and enhancing the performance. We showed that DTDY-CNNs extract more accurate frame-level speaker embeddings as well compared to TDY-CNNs. Detailed behaviors of DTDY-ResNet-34(x0.50) on extraction of speaker information were analyzed using speaker activation map (SAM) produced by modified gradient-weighted class activation mapping (Grad-CAM) for speaker verification. DTDY-ResNet-34(x0.50) effectively extracts speaker information from not only formant frequencies but also high frequency information of unvoiced phonemes, thus explaining its outstanding performance on text-independent speaker verification.

eess.AS↗

arXiv2022

Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection

2D convolution is widely used in sound event detection (SED) to recognize two dimensional time-frequency patterns of sound events. However, 2D convolution enforces translation equivariance on sound events along both time and frequency axis while frequency is not shift-invariant dimension. In order to improve physical consistency of 2D convolution on SED, we propose frequency dynamic convolution which applies kernel that adapts to frequency components of input. Frequency dynamic convolution outperforms the baseline by 6.3% in DESED validation dataset in terms of polyphonic sound detection score (PSDS). It also significantly outperforms other pre-existing content-adaptive methods on SED. In addition, by comparing class-wise F1 scores of baseline and frequency dynamic convolution, we showed that frequency dynamic convolution is especially more effective for detection of non-stationary sound events with intricate time-frequency patterns. From this result, we verified that frequency dynamic convolution is superior in recognizing frequency-dependent patterns.

eess.AS↗

arXiv2022

Data Augmentation and Squeeze-and-Excitation Network on Multiple Dimension for Sound Event Localization and Detection in Real Scenes

Performance of sound event localization and detection (SELD) in real scenes is limited by small size of SELD dataset, due to difficulty in obtaining sufficient amount of realistic multi-channel audio data recordings with accurate label. We used two main strategies to solve problems arising from the small real SELD dataset. First, we applied various data augmentation methods on all data dimensions: channel, frequency and time. We also propose original data augmentation method named Moderate Mixup in order to simulate situations where noise floor or interfering events exist. Second, we applied Squeeze-and-Excitation block on channel and frequency dimensions to efficiently extract feature characteristics. Result of our trained models on the STARSS22 test dataset achieved the best ER, F1, LE, and LR of 0.53, 49.8%, 16.0deg., and 56.2% respectively.

eess.AS↗

arXiv2022

Frequency Dependent Sound Event Detection for DCASE 2022 Challenge Task 4

While many deep learning methods on other domains have been applied to sound event detection (SED), differences between original domains of the methods and SED have not been appropriately considered so far. As SED uses audio data with two dimensions (time and frequency) for input, thorough comprehension on these two dimensions is essential for application of methods from other domains on SED. Previous works proved that methods those address on frequency dimension are especially powerful in SED. By applying FilterAugment and frequency dynamic convolution those are frequency dependent methods proposed to enhance SED performance, our submitted models achieved best PSDS1 of 0.4704 and best PSDS2 of 0.8224.

eess.AS↗

arXiv2022

Deep learning based cough detection camera using enhanced features

Coughing is a typical symptom of COVID-19. To detect and localize coughing sounds remotely, a convolutional neural network (CNN) based deep learning model was developed in this work and integrated with a sound camera for the visualization of the cough sounds. The cough detection model is a binary classifier of which the input is a two second acoustic feature and the output is one of two inferences (Cough or Others). Data augmentation was performed on the collected audio files to alleviate class imbalance and reflect various background noises in practical environments. For effective featuring of the cough sound, conventional features such as spectrograms, mel-scaled spectrograms, and mel-frequency cepstral coefficients (MFCC) were reinforced by utilizing their velocity (V) and acceleration (A) maps in this work. VGGNet, GoogLeNet, and ResNet were simplified to binary classifiers, and were named V-net, G-net, and R-net, respectively. To find the best combination of features and networks, training was performed for a total of 39 cases and the performance was confirmed using the test F1 score. Finally, a test F1 score of 91.9% (test accuracy of 97.2%) was achieved from G-net with the MFCC-V-A feature (named Spectroflow), an acoustic feature effective for use in cough detection. The trained cough detection model was integrated with a sound camera (i.e., one that visualizes sound sources using a beamforming microphone array). In a pilot test, the cough detection camera detected coughing sounds with an F1 score of 90.0% (accuracy of 96.0%), and the cough location in the camera image was tracked in real time.

eess.AS↗

arXiv2022

HRTF measurement for accurate sound localization cues

A new database of head-related transfer functions (HRTFs) for accurate sound source localization is presented through precise measurement and post-processing in terms of improved frequency bandwidth and causality of head-related impulse responses (HRIRs) for accurate spectral cue (SC) and interaural time difference (ITD), respectively. The improvement effects of the proposed methods on binaural sound localization cues were investigated. To achieve sufficient frequency bandwidth with a single source, a one-way sealed speaker module was designed to obtain wide band frequency response based on electro-acoustics, whereas most existing HRTF databases rely on a two-way vented loudspeaker that has multiple sources. The origin transfer function at the head center was obtained by the proposed measurement scheme using a 0 degree on-axis microphone to ensure accurate spectral cue pattern of HRTFs, whereas in the previous measurements with a 90 degree off-axis microphone, the magnitude response of the origin transfer function fluctuated and decreased with increasing frequency, causing erroneous SCs of HRTFs. To prevent discontinuity of ITD due to non-causality of ipsilateral HRTFs, obtained HRIRs were circularly shifted by time delay considering the head radius of the measurement subject. Finally, various sound localization cues such as ITD, interaural level difference (ILD), SC, and horizontal plane directivity (HPD) were derived from the presented HRTFs, and improvements on binaural sound localization cues were examined. As a result, accurate SC patterns of HRTFs were confirmed through the proposed measurement scheme using the 0 degree on-axis microphone, and continuous ITD patterns were obtained due to the non-causality compensation. Source codes and presented HRTF database are available to relevant research groups at GitHub (https://github.com/han-saram/HRTF-HATS-KAIST).

eess.AS↗

arXiv2022

Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemetic Analysis

In the field of text-independent speaker recognition, dynamic models that adapt along the time axis have been proposed to consider the phoneme-varying characteristics of speech. However, a detailed analysis of how dynamic models work depending on phonemes is insufficient. In this paper, we propose temporal dynamic CNN (TDY-CNN) that considers temporal variation of phonemes by applying kernels optimally adapting to each time bin. These kernels adapt to time bins by applying weighted sum of trained basis kernels. Then, an analysis of how adaptive kernels work on different phonemes in various layers is carried out. TDY-ResNet-38(x0.5) using six basis kernels improved an equal error rate (EER), the speaker verification performance, by 17.3% compared to the baseline model ResNet-38(x0.5). In addition, we showed that adaptive kernels depend on phoneme groups and are more phoneme-specific at early layers. The temporal dynamic model adapts itself to phonemes without explicitly given phoneme information during training, and results show the necessity to consider phoneme variation within utterances for more accurate and robust text-independent speaker verification.

eess.AS↗

arXiv2022

FilterAugment: An Acoustic Environmental Data Augmentation Method

Acoustic environments affect acoustic characteristics of sound to be recognized by physically interacting with sound wave propagation. Thus, training acoustic models for audio and speech tasks requires regularization on various acoustic environments in order to achieve robust performance in real life applications. We propose FilterAugment, a data augmentation method for regularization of acoustic models on various acoustic environments. FilterAugment mimics acoustic filters by applying different weights on frequency bands, therefore enables model to extract relevant information from wider frequency region. It is an improved version of frequency masking which masks information on random frequency bands. FilterAugment improved sound event detection (SED) model performance by 6.50% while frequency masking only improved 2.13% in terms of polyphonic sound detection score (PSDS). It achieved equal error rate (EER) of 1.22% when applied to a text-independent speaker verification model, outperforming model used frequency masking with EER of 1.26%. Prototype of FilterAugment was applied in our participation in DCASE 2021 challenge task 4, and played a major role in achieving the 3rd rank.

eess.AS↗

arXiv2021

Highly precise AMCW time-of-flight scanning sensor based on digital-parallel demodulation

In this paper, a novel amplitude-modulated continuous wave (AMCW) time-of-flight (ToF) scanning sensor based on digital-parallel demodulation is proposed and demonstrated in the aspect of distance measurement precision. Since digital-parallel demodulation utilizes a high-amplitude demodulation signal with zero-offset, the proposed sensor platform can maintain extremely high demodulation contrast. Meanwhile, as all cross correlated samples are calculated in parallel and in extremely short integration time, the proposed sensor platform can utilize a 2D laser scanning structure with a single photo detector, maintaining a moderate frame rate. This optical structure can increase the received optical SNR and remove the crosstalk of image pixel array. Based on these measurement properties, the proposed AMCW ToF scanning sensor shows highly precise 3D depth measurement performance. In this study, this precise measurement performance is explained in detail. Additionally, the actual measurement performance of the proposed sensor platform is experimentally validated under various conditions.

eess.SP↗

arXiv2021

Acoustic Signal based Non-Contact Ball Bearing Fault Diagnosis Using Adaptive Wavelet Denoising

This paper presents a non-contact fault diagnostic method for ball bearing using adaptive wavelet denoising, statistical-spectral acoustic features, and one-dimensional (1D) convolutional neural networks (CNN). The health conditions of the ball bearing are monitored by microphone under noisy conditions. To eliminate noise, adaptive wavelet denoising method based on kurtosis-entropy (KE) index is proposed. Multiple acoustic features are extracted base on expert knowledge. The 1D ResNet is used to classify the health conditions of the bearings. Case study is presented to examine the proposed method's capability to monitor the condition of ball bearing. The fault diagnosis results were compared with and without the adaptive wavelet denoising. The results show its effectiveness on the proposed fault diagnostic method using acoustic signals.

stat.AP↗

arXiv2021

Heavily Augmented Sound Event Detection utilizing Weak Predictions

The performances of Sound Event Detection (SED) systems are greatly limited by the difficulty in generating large strongly labeled dataset. In this work, we used two main approaches to overcome the lack of strongly labeled data. First, we applied heavy data augmentation on input features. Data augmentation methods used include not only conventional methods used in speech/audio domains but also our proposed method named FilterAugment. Second, we propose two methods to utilize weak predictions to enhance weakly supervised SED performance. As a result, we obtained the best PSDS1 of 0.4336 and best PSDS2 of 0.8161 on the DESED real validation dataset. This work is submitted to DCASE 2021 Task4 and is ranked on the 3rd place. Code availa-ble: https://github.com/frednam93/FilterAugSED.

eess.AS↗