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.
iSTFTNet speeds up mel-spectrogram vocoders without sacrificing quality.
CycleGAN-VC3 improves CycleGAN-VCs for mel-spectrogram conversion.
Study improves voice conversion model with Mel-spectrogram augmentation.
Adversarial attacks on spectrograms can fool audio classifiers trained on waveforms.
MaskCycleGAN-VC improves voice conversion without parallel data.
SpecGrad improves neural vocoder sound quality by adapting diffusion noise to log-mel spectrogram.
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…
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…
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs). The networks perform feature mapping between the spectral features of reverberant and clean speech. Long short term memory recurrent neural networks (LSTMs) are trained to map corrupted…
This paper proposes a Residual Convolutional Neural Network (ResNet) based on speech features and trained under Focal Loss to recognize emotion in speech. Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCCs) have shown the ability to characterize emotion better than just plain text. Furth…
To address Task 5 in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 challenge, in this paper, we propose an ensemble learning system. The proposed system consists of three different models, based on convolutional neural network and long short memory recurrent neural network. With extracted …
Novel fusion of autoencoders predicts sleepiness from speech.
This paper proposes a speech emotion recognition method based on speech features and speech transcriptions (text). Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCC) help retain emotion-related low-level characteristics in speech whereas text helps capture semantic meaning, both of which…
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…
DiffWave generates high-fidelity audio waveforms efficiently.
VPFD uses vocoder features for adversarial training in VC.
WaveGrad generates high-fidelity audio using gradient estimation.
This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the recognition of emotion in speech. Speech features such as Spectrograms and Mel-freq…
This paper explores how different audio signal representations affect topological signatures and their predictive power.
New method clusters infant vocalizations using topological data.
Paper aims to find joint representation between vocal tract geometry and speech sound acoustics.
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 investigated the training of a shared model for both text-to-speech (TTS) and voice conversion (VC) tasks. We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual attention mechanism as the shared model for both the TTS and VC tasks. This model can a…
Grad-TTS models speech from text using diffusion probabilistic techniques.
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 …
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…
This research investigates reliable local explanations for machine listening models.
Improved speech emotion recognition using pitch-synchronous single frequency filtering spectrogram.
Paper extends ICA to ISA with auxiliary variables for better speech representation learning.
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 …
Sound source separation has attracted attention from Music Information Retrieval(MIR) researchers, since it is related to many MIR tasks such as automatic lyric transcription, singer identification, and voice conversion. In this paper, we propose an intuitive spectrogram-based model for source separation by adapting U-…
PriorGrad improves speech synthesis models by using data-dependent adaptive priors.
Acoustic scene classification is the task of identifying the scene from which the audio signal is recorded. Convolutional neural network (CNN) models are widely adopted with proven successes in acoustic scene classification. However, there is little insight on how an audio scene is perceived in CNN, as what have been d…
Improved U-Nets with various intermediate blocks enhance singing voice separation.
Sound event detection systems typically consist of two stages: extracting hand-crafted features from the raw audio waveform, and learning a mapping between these features and the target sound events using a classifier. Recently, the focus of sound event detection research has been mostly shifted to the latter stage usi…
This paper proposes a multichannel source separation technique called the multichannel variational autoencoder (MVAE) method, which uses a conditional VAE (CVAE) to model and estimate the power spectrograms of the sources in a mixture. By training the CVAE using the spectrograms of training examples with source-class l…
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) …
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…
A new RBM model handles both linear and log-amplitude spectrograms.
We introduce the convolutional spectral kernel (CSK), a novel family of non-stationary, nonparametric covariance kernels for Gaussian process (GP) models, derived from the convolution between two imaginary radial basis functions. We present a principled framework to interpret CSK, as well as other deep probabilistic mo…
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…
Optimal transport as a loss for machine learning optimization problems has recently gained a lot of attention. Building upon recent advances in computational optimal transport, we develop an optimal transport non-negative matrix factorization (NMF) algorithm for supervised speech blind source separation (BSS). Optimal …
Paper presents a deep learning framework for classifying respiratory anomalies and lung diseases from sound recordings.
Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks (GANs) in a variety of image processing tasks, we explore the potential of cond…
Graph neural networks improve music genre classification on audio datasets.
X-DC improves speech separation by making DNNs more interpretable.
mGENRE improves multilingual entity linking with autoregressive sequence prediction.