SubSpectral Normalization for Neural Audio Data Processing
Convolutional Neural Networks are widely used in various machine learning domains. In image processing, the features can be obtained by applying 2D convolution to all spatial dimensions of the input. However, in the audio case, frequency domain input like Mel-Spectrogram has different and unique characteristics in the frequency dimension. Thus, there is a need for a method that allows the 2D convolution layer to handle the frequency dimension differently. In this work, we introduce SubSpectral Normalization (SSN), which splits the input frequency dimension into several groups (sub-bands) and performs a different normalization for each group. SSN also includes an affine transformation that can be applied to each group. Our method removes the inter-frequency deflection while the network learns a frequency-aware characteristic. In the experiments with audio data, we observed that SSN can efficiently improve the network's performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Keyword SpottingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Towards Robust Domain Generalization in 2D Neural Audio Processing
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to ge…
Acoustic Scene ClassificationDomain GeneralizationKeyword SpottingScene Classification+1Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to ge…
Acoustic Scene ClassificationDomain GeneralizationScene ClassificationHUI-Audio-Corpus-German: A high quality TTS dataset
The increasing availability of audio data on the internet lead to a multitude of datasets for development and training of text to speech applications, based on neural networks. Highly differing quality of voice, low samp…
Text Normalizationtext-to-speechText to SpeechVocal Bursts Intensity PredictionStatistics-aware Audio-visual Deepfake Detector
In this paper, we propose an enhanced audio-visual deep detection method. Recent methods in audio-visual deepfake detection mostly assess the synchronization between audio and visual features. Although they have shown pr…
DeepFake DetectionFace SwappingSpectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation
Separating vocal elements from musical tracks is a longstanding challenge in audio signal processing. This study tackles the distinct separation of vocal components from musical spectrograms. We employ the Short Time Fou…
Audio Signal ProcessingAudio Source Separation