Online audio advertising is a particular form of advertising used abundantly in online music streaming services. In these platforms, which tend to host tens of thousands of unique audio advertisements (ads), providing high quality ads ensures a better user experience and results in longer user engagement. Therefore, th…
On-device research index
arXiv research
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “audio quality”
Paper uses SSL models' uncertainty to predict audio quality efficiently.
problem Efficiently predicting audio quality in low-resource settings.
method Leverages self-supervised learning models' uncertainty measures.
result Uncertainty measures correlate with MOS scores in SSL models.
Unified model for audio control and style transfer.
problem Explicit control and style transfer in music generation.
method Diffusion autoencoders for semantic feature extraction, disentanglement using adversarial criterion.
result Model generates audio matching timbre targets with specified structure.
WaveGrad generates high-fidelity audio using gradient estimation.
problem Generating high-fidelity audio efficiently.
method Conditional model using score matching and diffusion models, iteratively refining a Gaussian white noise signal.
result WaveGrad can generate high-fidelity audio samples using as few as six iterations.
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…
Recently, there has been great interest in the field of audio style transfer, where a stylized audio is generated by imposing the style of a reference audio on the content of a target audio. We improve on the current approaches which use neural networks to extract the content and the style of the audio signal and propo…
We frame the problem of selecting an optimal audio encoding scheme as a supervised learning task. Through uniform convergence theory, we guarantee approximately optimal codec selection while controlling for selection bias. We present rigorous statistical guarantees for the codec selection problem that hold for arbitrar…
New method allows real-time audio synthesis using non-causal convolutions.
problem Real-time audio synthesis limitations due to offline model constraints.
method Post-training reconfiguration of non-causal models for real-time buffer-based processing.
result Non-causal streaming models can be transformed from offline-trained models without quality loss.
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.
We present LumièreNet, a simple, modular, and completely deep-learning based architecture that synthesizes, high quality, full-pose headshot lecture videos from instructor's new audio narration of any length. Unlike prior works, LumièreNet is entirely composed of trainable neural network modules to learn mapping functi…
GGAN improves audio representation learning with fewer labels.
problem Learning representations for specific tasks from unlabelled data.
method Guided Generative Adversarial Neural Network (GGAN).
result GGAN learns better representations with fewer labelled data.
Audio source separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals). Deep learning models are the state-of-the-art in source separation, given that the mixture to be separated is similar to the mixtures the deep model was tr…
Time-frequency (TF) representations provide powerful and intuitive features for the analysis of time series such as audio. But still, generative modeling of audio in the TF domain is a subtle matter. Consequently, neural audio synthesis widely relies on directly modeling the waveform and previous attempts at unconditio…
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…
Efficient neural network for audio source separation.
problem End-to-end general purpose audio source separation.
method SuDoRMRF structure with simple one-dimensional convolutions for feature aggregation.
result SuDoRMRF achieves high quality audio source separation with minimal computational resources.
Proposes COALA method for learning audio representations aligned with tags.
problem Lack of annotated data for high-performance audio representation learning.
method Aligns latent representations of audio and tags using a contrastive loss.
result Audio embedding model captures both acoustic and semantic characteristics.
Paper proposes a method to create smaller, more efficient deep generative audio models.
problem High computation cost and complexity of deep generative models in audio applications.
method Developed a method for structured trimming of deep generative audio models.
result 95% of model weights can be removed without significant degradation in accuracy.
We augment the nonnegative matrix factorization method for audio source separation with cues about directionality of sound propagation. This improves separation quality greatly and removes the need for training data, with only a twofold increase in run time. This is the first method which can exploit directional inform…
In this work, we address the problem of musical timbre transfer, where the goal is to manipulate the timbre of a sound sample from one instrument to match another instrument while preserving other musical content, such as pitch, rhythm, and loudness. In principle, one could apply image-based style transfer techniques t…
Incremental Text to Speech for Neural Sequence-to-Sequence Models using Reinforcement Learningeess.AS
Improves text-to-speech speed by interleaving character reading and audio synthesis.
problem Latency in text-to-speech models limits their use in time-sensitive tasks.
method Reinforcement learning to train an agent to choose the order of character reading and audio synthesis.
result The proposed method successfully balances latency and audio quality.
High-Fidelity Audio Generation and Representation Learning with Guided Adversarial Autoencodereess.AS
Proposes GAAE for high-fidelity audio generation and representation learning.
problem Lack of usable representations and high-fidelity audio generation from unsupervised learning.
method Guided Adversarial Autoencoder (GAAE) leveraging a small percentage of labelled data.
result Generates high-fidelity audio with superior quality and learns powerful representations.
Generative adversarial network improves audio inpainting for long gaps.
problem Generating missing audio content in long-range gaps using WGAN.
method Proposed WGAN architecture with short-range and long-range neighboring borders.
result The proposed model outperforms classical WGAN in reconstructing high-frequency content.
Paper tackles GAN instability in audio and speech signals using a new similarity metric.
problem Improving stability of LS-GANs for audio and speech signals.
method Proposes a new similarity metric in unitary space of Schur decomposition for 2D audio and speech representations.
result Enhanced stability in training with less mode collapse compared to baseline GANs.
CrossFilter tackles noisy labels in audio tagging.
problem Noisy labels in large audio datasets.
method CrossFilter framework using multiple representations and multi-task learning.
result Improves audio tagging performance on FSDKaggle2018 and FSDKaggle2019 datasets.
Deep learning models generate music with arbitrary control strategies.
problem Lack of efficient methods for generating music with arbitrary control.
method Deep generative models learn to navigate arbitrary sound spaces.
result Deep learning enables high-quality, arbitrary sound synthesis.
In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled train…
Neural codec for high-fidelity audio compression.
problem Efficiently compress audio while maintaining high quality.
method End-to-end neural network architecture with quantized latent space, single multiscale spectrogram adversary, loss balancer mechanism, and lightweight Transformer compression.
result 40% compression with no loss in quality, faster than real-time.
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…
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…
This work aims to examine one of the cornerstone problems of Musical Instrument Retrieval (MIR), in particular, instrument classification. IRMAS (Instrument recognition in Musical Audio Signals) data set is chosen for this purpose. The data includes musical clips recorded from various sources in the last century, thus …
Novel unsupervised audio source separation using generative priors.
problem Challenges of supervised methods in audio source separation.
method Generative priors trained on individual sources using projected gradient descent optimization.
result Effective recovery of constituent sources with good-quality estimates.
New method improves speech synthesis quality.
problem Efficiently train parallel speech synthesis models.
method Spectral energy distance for implicit generative models.
result State-of-the-art generation quality achieved.
The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process --- creating audio samples from a score and instrument information --- is modeled using generative neural networks. This paper describes a neural music synthesis model with fl…
Data-Efficient Weakly Supervised Learning for Low-Resource Audio Event Detection Using Deep Learningcs.SD
We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are "weakly labelled" having only a list of events present in each rec…
Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While state-of-the-art machine learning techniques, such as deep neural networks, can provi…
In order to efficiently transmit and store speech signals, speech codecs create a minimally redundant representation of the input signal which is then decoded at the receiver with the best possible perceptual quality. In this work we demonstrate that a neural network architecture based on VQ-VAE with a WaveNet decoder …
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…
We present RUSLAN -- a new open Russian spoken language corpus for the text-to-speech task. RUSLAN contains 22200 audio samples with text annotations -- more than 31 hours of high-quality speech of one person -- being the largest annotated Russian corpus in terms of speech duration for a single speaker. We trained an e…
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…
This paper proposes a zero-shot learning approach for audio classification based on the textual information about class labels without any audio samples from target classes. We propose an audio classification system built on the bilinear model, which takes audio feature embeddings and semantic class label embeddings as…
Develops deep NMF models using β-divergences for feature extraction.
problem Inadequate evaluation metrics for deep NMF on diverse datasets.
method Introduces new deep NMF models using Kullback-Leibler divergence.
result Improves feature extraction quality across different types of data.
Deep Audio Priorcs.SD
Deep convolutional neural networks are known to specialize in distilling compact and robust prior from a large amount of data. We are interested in applying deep networks in the absence of training dataset. In this paper, we introduce deep audio prior (DAP) which leverages the structure of a network and the temporal in…
Spatial audio is an essential medium to audiences for 3D visual and auditory experience. However, the recording devices and techniques are expensive or inaccessible to the general public. In this work, we propose a self-supervised audio spatialization network that can generate spatial audio given the corresponding vide…
This paper explores how different audio signal representations affect topological signatures and their predictive power.
problem The impact of different signal representations on topological signatures and their predictive power.
method The study compares three different signal representations (embedding, spectrogram, and spectrogram zeroes) and evaluates their topological signatures for speaker gender, vowel type, and individual prediction.
result Topological signatures from spectrogram zeroes offer the best improvement for gender prediction, and different representations are complementary.
Method learns audio embeddings with contextualized tags.
problem Align audio and tags for cross-modal tasks.
method Audio autoencoder, word embeddings, multi-head self-attention, contrastive loss.
result Multi-head self-attention improves audio representations.
Study improves radio show segmentation using audio embeddings.
problem Automated segmentation of radio shows.
method Created audio embeddings from multi-class classification tasks on different datasets, evaluated performance against text-only baseline.
result Audio embeddings from non-speech sound event classification significantly outperformed text-only baseline by 32.3% in F1-measure.
Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating sentences one token at a time from left to right. This paper studies the influence o…
We extend the Deep Image Prior (DIP) framework to one-dimensional signals. DIP is using a randomly initialized convolutional neural network (CNN) to solve linear inverse problems by optimizing over weights to fit the observed measurements. Our main finding is that properly tuned one-dimensional convolutional architectu…