A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
This paper shows the susceptibility of spectrogram-based audio classifiers to adversarial attacks and the transferability of such attacks to audio waveforms. Some commonly used adversarial attacks to images have been applied to Mel-frequency and short-time Fourier transform spectrograms, and such perturbed spectrograms…
A new RBM model handles both linear and log-amplitude spectrograms.
AaSP improves audio self-supervised learning by addressing aliasing issues.
End-to-end neural network based approaches to audio modelling are generally outperformed by models trained on high-level data representations. In this paper we present preliminary work that shows the feasibility of training the first layers of a deep convolutional neural network (CNN) model to learn the commonly-used l…
We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method estimates the temporal gap between two short audio segments extracted at random fr…
iSTFTNet speeds up mel-spectrogram vocoders without sacrificing quality.
Nonnegative matrix factorization (NMF) is now a common tool for audio source separation. When learning NMF on large audio databases, one major drawback is that the complexity in time is O(FKN) when updating the dictionary (where (F;N) is the dimension of the input power spectrograms, and K the number of basis spectra),…
Neural codec for high-fidelity audio compression.
MASnet enhances speech on mobile devices with low latency.
Music genre is arguably one of the most important and discriminative information for music and audio content. Visual representation based approaches have been explored on spectrograms for music genre classification. However, lack of quality data and augmentation techniques makes it difficult to employ deep learning tec…
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the safety of machine learning models since the adversarial attacks can fool such model…
Convolutional neural network (CNN) architectures have originated and revolutionized machine learning for images. In order to take advantage of CNNs in predictive modeling with audio data, standard FFT-based signal processing methods are often applied to convert the raw audio waveforms into an image-like representations…
Novel fusion of autoencoders predicts sleepiness from speech.
In this paper, we address the problem of reconstructing a time-domain signal (or a phase spectrogram) solely from a magnitude spectrogram. Since magnitude spectrograms do not contain phase information, we must restore or infer phase information to reconstruct a time-domain signal. One widely used approach for dealing w…
This paper explores how different audio signal representations affect topological signatures and their predictive power.
Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can be more tractably modelled in two-dimensional time-frequency representations suc…
In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training. Our main contribution is in demonstrating that adding a high-level feature loss term, extracted from the spectrograms using a VGG net, can improve…
Deep neural networks with convolutional layers usually process the entire spectrogram of an audio signal with the same time-frequency resolutions, number of filters, and dimensionality reduction scale. According to the constant-Q transform, good features can be extracted from audio signals if the low frequency bands ar…
WaveGrad generates high-fidelity audio using gradient estimation.
In this paper we present ensembles of classifiers for automated animal audio classification, exploiting different data augmentation techniques for training Convolutional Neural Networks (CNNs). The specific animal audio classification problems are i) birds and ii) cat sounds, whose datasets are freely available. We tra…
Gaussian process (GP) audio source separation is a time-domain approach that circumvents the inherent phase approximation issue of spectrogram based methods. Furthermore, through its kernel, GPs elegantly incorporate prior knowledge about the sources into the separation model. Despite these compelling advantages, the c…
CycleGAN-VC3 improves CycleGAN-VCs for mel-spectrogram conversion.
DiffWave generates high-fidelity audio waveforms efficiently.
In this paper we propose WaveGlow: a flow-based network capable of generating high quality speech from mel-spectrograms. WaveGlow combines insights from Glow and WaveNet in order to provide fast, efficient and high-quality audio synthesis, without the need for auto-regression. WaveGlow is implemented using only a singl…
Paper tackles GAN instability in audio and speech signals using a new similarity metric.
SpecGrad improves neural vocoder sound quality by adapting diffusion noise to log-mel spectrogram.
A typical audio signal processing pipeline includes multiple disjoint analysis stages, including calculation of a time-frequency representation followed by spectrogram-based feature analysis. We show how time-frequency analysis and nonnegative matrix factorisation can be jointly formulated as a spectral mixture Gaussia…
Neural network-based vocoders have recently demonstrated the powerful ability to synthesize high-quality speech. These models usually generate samples by conditioning on spectral features, such as Mel-spectrogram and fundamental frequency, which is crucial to speech synthesis. However, the feature extraction procession…
We present a voice conversion solution using recurrent sequence to sequence modeling for DNNs. Our solution takes advantage of recent advances in attention based modeling in the fields of Neural Machine Translation (NMT), Text-to-Speech (TTS) and Automatic Speech Recognition (ASR). The problem consists of converting be…
Previous attempts at music artist classification use frame level audio features which summarize frequency content within short intervals of time. Comparatively, more recent music information retrieval tasks take advantage of temporal structure in audio spectrograms using deep convolutional and recurrent models. This pa…
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
In this paper we propose a novel environmental sound classification approach incorporating unsupervised feature learning from codebook via spherical -Means++ algorithm and a new architecture for high-level data augmentation. The audio signal is transformed into a 2D representation using a discrete wavelet transform …
Sound synthesis is a complex field that requires domain expertise. Manual tuning of synthesizer parameters to match a specific sound can be an exhaustive task, even for experienced sound engineers. In this paper, we introduce InverSynth - an automatic method for synthesizer parameters tuning to match a given input soun…
Recent progress in deep learning for audio synthesis opens the way to models that directly produce the waveform, shifting away from the traditional paradigm of relying on vocoders or MIDI synthesizers for speech or music generation. Despite their successes, current state-of-the-art neural audio synthesizers such as Wav…
Even in the absence of any explicit semantic annotation, vast collections of audio recordings provide valuable information for learning the categorical structure of sounds. We consider several class-agnostic semantic constraints that apply to unlabeled nonspeech audio: (i) noise and translations in time do not change t…
Non-negative matrix factorization is a problem of dimensionality reduction and source separation of data that has been widely used in many fields since it was studied in depth in 1999 by Lee and Seung, including in compression of data, document clustering, processing of audio spectrograms and astronomy. In this work we…
MaskCycleGAN-VC improves voice conversion without parallel data.
Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players perform steps on a dance platform in synchronization with music as directed by on-screen step charts. While many step charts are available in standardized packs, players may grow tired of existing charts, or wish to dance to a song for which no …
This paper deals with a multichannel audio source separation problem under underdetermined conditions. Multichannel Non-negative Matrix Factorization (MNMF) is one of powerful approaches, which adopts the NMF concept for source power spectrogram modeling. This concept is also employed in Independent Low-Rank Matrix Ana…
Being able to predict whether a song can be a hit has impor- tant applications in the music industry. Although it is true that the popularity of a song can be greatly affected by exter- nal factors such as social and commercial influences, to which degree audio features computed from musical signals (whom we regard as …
In acoustic scene classification researches, audio segment is usually split into multiple samples. Majority voting is then utilized to ensemble the results of the samples. In this paper, we propose a punishment voting algorithm based on the super categories construction method for acoustic scene classification. Specifi…
The current methodology in tackling Acoustic Scene Classification (ASC) task can be described in two steps, preprocessing of the audio waveform into log-mel spectrogram and then using it as the input representation for Convolutional Neural Network (CNN). This paradigm shift occurs after DCASE 2016 where this framework …
Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end source separation in the time-domain, which allows modelling phase information and…
In the past, Acoustic Scene Classification systems have been based on hand crafting audio features that are input to a classifier. Nowadays, the common trend is to adopt data driven techniques, e.g., deep learning, where audio representations are learned from data. In this paper, we propose a system that consists of a …
Wavelet Networks learn from raw time-series data, outperforming conventional CNNs.
Early detection and treatment of depression is essential in promoting remission, preventing relapse, and reducing the emotional burden of the disease. Current diagnoses are primarily subjective, inconsistent across professionals, and expensive for individuals who may be in urgent need of help. This paper proposes a nov…
New method improves speech synthesis quality.
Generates music with video emotion using deep neural networks.