Generative adversarial network improves signal reconstruction from magnitude spectrograms.
problem Reconstructing a time-domain signal from a magnitude spectrogram.
method Deep neural network and generative adversarial network approach.
result Our method reconstructs signals faster with higher quality than the Griffin-Lim method.
Deep model generates high-quality speech from spectrograms.
problem Speech reconstruction from spectrograms.
method Deep generative model with Gaussian and von Mises distributions for magnitude and phase, variational autoencoder framework.
result Generated speech has high perceptual quality and intelligibility.
iSTFTNet speeds up mel-spectrogram vocoders without sacrificing quality.
problem Efficiently converting mel-spectrograms to speech with minimal computation.
method Replaces convolutional layers with iSTFT after frequency dimension reduction.
result Significant reduction in computational cost with comparable quality.
Improved U-Nets with various intermediate blocks enhance singing voice separation.
problem Improving singing voice separation accuracy using U-Net architectures.
method Implemented and compared U-Nets with different intermediate spectrogram transformation blocks.
result A specific block type achieves state-of-the-art SDR by 0.9 dB.
Adversarial attacks on spectrograms can fool audio classifiers trained on waveforms.
problem Susceptibility of audio classifiers to adversarial attacks on spectrograms.
method Applying adversarial attacks to spectrograms and reconstructing audio waveforms.
result Perturbed spectrograms can fool 2D CNNs and 1D CNNs trained on audio waveforms.
Spectrogram-Channels U-Net separates sounds by treating each channel as a source's spectrogram.
problem Sound source separation in music information retrieval.
method Adapting U-Net to treat each channel of the output as a source's spectrogram, balancing volumes between sources.
result State-of-the-art performance on singing voice and multi-instrument separation.
This paper aims to address two issues existing in the current speech enhancement methods: 1) the difficulty of phase estimations; 2) a single objective function cannot consider multiple metrics simultaneously. To solve the first problem, we propose a novel convolutional neural network (CNN) model for complex spectrogra…
Improved speech emotion recognition using pitch-synchronous single frequency filtering spectrogram.
problem Uncertainty principles in STFT spectrogram limit time and frequency resolutions.
method Modified SFF spectrogram by averaging amplitudes between GCI locations, named pitch-synchronous SFF spectrogram.
result Improved SER accuracy (63.95% to 70.4%) on IEMOCAP dataset.
Study improves voice conversion model with Mel-spectrogram augmentation.
problem Insufficient speech pairs data for training sequence-to-sequence voice conversion models.
method Experimented with Mel-spectrogram augmentation using SpecAugment policies and proposed new augmentation policies.
result Time axis warping policies showed better performance in training the voice conversion model.
CycleGAN-VC3 improves CycleGAN-VCs for mel-spectrogram conversion.
problem Ambiguity in CycleGAN-VC/VC2 effectiveness for mel-spectrogram conversion.
method Proposes CycleGAN-VC3 with time-frequency adaptive normalization (TFAN).
result CycleGAN-VC3 outperforms or matches CycleGAN-VC2 for mel-spectrogram conversion.
Automatic Music Transcription (AMT) consists in automatically estimating the notes in an audio recording, through three attributes: onset time, duration and pitch. Probabilistic Latent Component Analysis (PLCA) has become very popular for this task. PLCA is a spectrogram factorization method, able to model a magnitude …
Improved music source separation using spectrogram feature loss.
problem Music source separation quality improvement.
method Added a high-level feature loss term from spectrograms using a VGG net to a deep learning model.
result Improvement in separation quality of drums and vocals from songs.
VoiceFilter separates target speaker from multi-speaker signals.
problem Speech recognition in multi-speaker environments.
method Speaker recognition network and spectrogram masking network trained together.
result Significant reduction in speech recognition WER on multi-speaker signals.
Paper proposes MVAE for semi-blind source separation using CVAE.
problem Semi-blind source separation in multichannel mixtures.
method Multichannel variational autoencoder (MVAE) with conditional VAE (CVAE).
result MVAE outperforms baseline method in separation performance.
Advanced deep learning model improves speech enhancement by estimating phase accurately.
problem Difficulty in estimating the phase of clean speech in speech enhancement.
method Proposes Deep Complex U-Net, polar coordinate-wise complex-valued masking, and wSDR loss function.
result Achieves state-of-the-art performance in all metrics, outperforming previous approaches.
End-to-end models perform better with learned log-scaled mel-spectrogram features.
problem End-to-end neural network models struggle with performance compared to models using high-level data representations.
method Trained first layers of a CNN model on log-scaled mel-spectrogram transformation and then used these learned features to initialize an end-to-end CNN classifier.
result Convergence and performance on ESC-50 dataset are similar to a model trained on pre-processed log-scaled mel-spectrogram features.
Novel CSK kernel improves GP model generalization for non-stationary patterns.
problem Improving generalization of Gaussian process models for non-stationary data.
method Introduced convolutional spectral kernel (CSK) derived from convolution of imaginary radial basis functions, using Fourier transform for interpretation.
result CSK improves GP model generalization on spatiotemporal datasets.
New neural network separates singing voices from music using cross entropy loss.
problem Separating singing voices from music accompaniment.
method Deep Convolutional Neural Network (CNN) trained with Ideal Binary Mask (IBM) and cross entropy loss.
result Proposed CNN outperforms existing systems in MIREX evaluations.
A new RBM model handles both linear and log-amplitude spectrograms.
problem Handling amplitude spectra with existing models.
method Proposed gamma-Bernoulli RBM that uses gamma distribution.
result The model can naturally handle positive numbers and log-amplitude spectrograms.
Optimal transport improves speech BSS by better aligning spectrogram frequencies.
problem Speech BSS with improved frequency alignment.
method Developed optimal transport NMF for supervised speech BSS.
result Optimal transport NMF leads to better perceptual results than Euclidean NMF.
Conditional GANs enhance speech in noisy conditions.
problem Improving speech system performance in noisy environments.
method Conditional Generative Adversarial Networks (cGANs) trained on spectrograms.
result cGAN method outperforms classical SE algorithms and is comparable to deep neural networks.
DiffWave generates high-fidelity audio waveforms efficiently.
problem Conditional and unconditional audio waveform generation.
method Non-autoregressive diffusion model using Markov chain synthesis.
result DiffWave produces high-quality audios in various tasks.
WaveGlow generates high-quality speech from spectrograms.
problem Speech synthesis quality and efficiency.
method WaveGlow combines Glow and WaveNet insights, using a single network and cost function for efficient, high-quality audio synthesis.
result WaveGlow produces audio samples at over 500 kHz, matching WaveNet quality.
Paper presents a deep learning framework for classifying respiratory anomalies and lung diseases from sound recordings.
problem Classifying respiratory anomalies and lung diseases from respiratory sound recordings.
method The framework uses front-end feature extraction to transform sound into spectrograms, and a deep learning network to classify these features.
result The proposed deep learning system outperforms current state-of-the-art methods on the ICBHI benchmark dataset.
Study compares new audio representation methods for limited data music retrieval.
problem Improving machine learning for audio data with limited training data.
method Investigated mel-spectrogram and Mel scattering representations, and augmented target loss function.
result All proposed methods outperform standard mel-spectrogram when using limited data.
Graph neural networks improve music genre classification on audio datasets.
problem Difficulty in applying deep learning on spectrograms due to lack of quality data and augmentation.
method Combination of CNN and Graph Neural Networks (GNN) with Siamese Neural Networks.
result Achieved state-of-the-art results on GTZAN and AudioSet datasets.
SpecGrad improves neural vocoder sound quality by adapting diffusion noise to log-mel spectrogram.
problem Improving neural vocoder sound quality, especially in high-frequency bands.
method Adapting the diffusion noise distribution to the conditioning log-mel spectrogram through time-varying filtering.
result SpecGrad generates higher-fidelity speech waveform than conventional DDPM-based neural vocoders.
X-DC improves speech separation by making DNNs more interpretable.
problem Black-box nature of DNNs in speech separation tasks.
method Introduces X-DC, a DNN architecture that interprets as spectrogram template fitting followed by Wiener filtering.
result X-DC achieves comparable speech separation performance to DC but with enhanced interpretability.
MaskCycleGAN-VC improves voice conversion without parallel data.
problem Limited ability to convert mel-spectrogram data without parallel data.
method Integrates a novel auxiliary task called filling in frames (FIF) to learn time-frequency structures.
result MaskCycleGAN-VC outperforms existing methods with similar model size.
CLCNet improves noise reduction in hearing aids with deep learning.
problem Noise reduction in hearing aids is challenging due to real-time and frequency resolution constraints.
method Proposes CLCNet, a deep learning framework based on complex linear coding.
result CLCNet outperforms traditional methods in noisy environments.
Deep learning detects atrial fibrillation with high accuracy.
problem Detecting atrial fibrillation in ECG signals.
method Extracted deep features from spectrograms using convolutional networks.
result Convolutional network achieved 93.16% classification accuracy.
AaSP improves audio self-supervised learning by addressing aliasing issues.
problem Alias issues in audio spectrogram transformers.
method AaSP combines aliasing-aware patch representation, teacher-student masked modeling, cross-attention predictor, and contrastive regularization.
result AaSP learns more stable representations that integrate high-frequency cues.
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
problem Efficiently synthesizing high-fidelity speech.
method Improved iSTFTNet using 1D-2D CNNs for temporal and spectrogram structures.
result iSTFTNet2 is faster and more lightweight with comparable speech quality.
ResNet with Focal Loss improves speech emotion recognition.
problem Speech emotion recognition using plain text features is insufficient.
method Residual Convolutional Neural Network (ResNet) trained with Focal Loss.
result Focal Loss enhances model's focus on hard examples.
ConvNet classifies whale vocalizations and ambient noise in acoustic recordings.
problem Automated detection and classification of marine mammal vocalizations in acoustic recordings.
method Convolutional Neural Network with a novel acoustic representation.
result Classifier accurately detects and classifies whale vocalizations and ambient noise.
Mobile devices learn audio representations using self-supervised methods.
problem Learning general-purpose audio representations on mobile devices.
method Temporal context exploitation in spectrogram domain, inspired by Word2Vec.
result Self-supervised models can produce embeddings that perform similarly to fully supervised models.
This research investigates reliable local explanations for machine listening models.
problem Generating reliable local explanations for machine listening models.
method Investigates the sensitivity of SoundLIME explanations to input perturbations and proposes a novel method for identifying suitable content types.
result SoundLIME explanations are sensitive to the content in occluded input regions, and the average magnitude of input mel-spectrogram bins is the most suitable content type for temporal explanations.
Paper proposes a novel unsupervised feature learning approach for environmental sound classification.
problem Classifying environmental sounds without labeled data.
method Cycle-consistent GAN for high-level data augmentation, unsupervised feature learning, codebook construction.
result Improves classification rate by 3.51% to 14.34% compared to state-of-the-art classifiers.
MASnet enhances speech on mobile devices with low latency.
problem Efficiently enhancing speech on mobile devices with low latency.
method MASnet processes linear-scale spectrograms, using ratio masks to enhance noisy frames, and operates in low-latency incremental inference mode.
result MASnet achieves efficient speech enhancement with low latency, reducing FMA/s operations.
A new neural network separates singing voices more effectively.
problem Separating singing voices from mixed signals with high accuracy.
method MBR-FCN that processes different frequency bands with varying resolutions and filters.
result The MBR-FCN achieves better performance with fewer parameters.
SRMD uses random features for efficient time-frequency analysis.
problem Efficiently analyzing time-series data with low computational cost.
method Sparse Random Mode Decomposition (SRMD) constructs a sparse approximation to the spectrogram.
result SRMD outperforms other methods in signal representation, outlier removal, and mode decomposition.
Improves speech separation by integrating time and frequency domains.
problem Speech separation using deep learning techniques.
method Proposes a framework that combines time and frequency domain features, using an embedding network and clustering.
result Obtained state-of-the-art results on WSJ0-2mix dataset.
Novel fusion of autoencoders predicts sleepiness from speech.
problem Predicting sleepiness from speech recordings.
method Attention-based and recurrent sequence to sequence autoencoders for unsupervised representation learning.
result Fusion of autoencoders' representations achieves higher correlation with sleepiness scales.
Improved audio source separation for underdetermined conditions.
problem Underdetermined source separation challenges for non-NMF-compliant sound sources.
method Generalized Multichannel Variational Autoencoder (GMVAE) that extends Conditional VAE for underdetermined cases.
result The GMVAE method outperformed MNMF in underdetermined source separation tasks.
PBN combines generative and discriminative capabilities in a neural network.
problem Combining generative and discriminative capabilities in neural networks.
method Convolutional PBN, sharing FF-NN embodiment, combining generative and discriminative qualities.
result PBN shows excellent qualities from either generative or discriminative viewpoint.
Paper detects adversarial attacks in sound classification models.
problem Adversarial attacks threaten data-driven models, especially in sound classification.
method Detects adversarial subspaces in unitary vector domain using chordal distance and generalized Schur decomposition.
result Regularized logistic regression detector outperforms other approaches on benchmark datasets.
This paper improves multichannel speech enhancement using complex ratio masking and channel-attention.
problem Limited performance of deep learning methods in multichannel speech enhancement.
method Introduces complex ratio masking and channel-attention mechanism inside a U-Net architecture.
result Demonstrates superior performance on the CHiME-3 dataset.
DR-NMF uses unfolded ISTA for speech separation, offering interpretability and speed.
problem Speech separation in noisy environments.
method DR-NMF is a recurrent neural network that unfolds ISTA iterations for NMF of spectrograms.
result DR-NMF outperforms NMF and LSTM networks in speech separation.