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.
Synthesizes images from audio and visual data using spike-based autoencoders.
Nowadays, CAPTCHAs are computer generated tests that human can pass but current computer systems can not. They have common usage in various web services in order to be able to detect a human from computer programs autonomously. In this way, owners can protect their web services from bots. In addition to visual CAPTCHAs…
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
Blow converts non-parallel raw audio voices efficiently.
Level assessment for foreign language students is necessary for putting them in the right level group, furthermore, interviewing students is a very time-consuming task, so we propose to automate the evaluation of speaker fluency level by implementing machine learning techniques. This work presents an audio processing s…
New method for one-shot timbre transfer in music.
Paper uses SSL models' uncertainty to predict audio quality efficiently.
This research converts visual information into audio for users to perceive.
Paper tackles score following in full-page sheet music images.
Accurate on-device keyword spotting (KWS) with low false accept and false reject rate is crucial to customer experience for far-field voice control of conversational agents. It is particularly challenging to maintain low false reject rate in real world conditions where there is (a) ambient noise from external sources s…
ACI converts call center conversations into actionable data.
Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 video-level labels. We examine fully connected Deep Neural Networks (DNNs)…
End-to-end ASR error detection using audio-transcript entailment.
New system tracks musical performances in raw sheet images without preprocessing.
We present a deep learning method for singing voice conversion. The proposed network is not conditioned on the text or on the notes, and it directly converts the audio of one singer to the voice of another. Training is performed without any form of supervision: no lyrics or any kind of phonetic features, no notes, and …
CycleGAN-VC3 improves CycleGAN-VCs for mel-spectrogram conversion.
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…
Adversarial attacks on spectrograms can fool audio classifiers trained on waveforms.
This paper proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed method, called ConvS2S-VC, has three key features. First, it uses a model with a fully…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
FastVoiceGrad speeds up VC to one step, matching or surpassing quality.
MaskCycleGAN-VC improves voice conversion without parallel data.
The fashion industry is establishing its presence on a number of visual-centric social media like Instagram. This creates an interesting clash as fashion brands that have traditionally practiced highly creative and editorialized image marketing now have to engage with people on the platform that epitomizes impromptu, r…
GEM learns a manifold for cross-modal data, capturing structure without modality dependence.
New method converts ANN gates to SNNs with AMOS neurons for improved image classification.
This paper addresses the problem of localizing audio sources using binaural measurements. We propose a supervised formulation that simultaneously localizes multiple sources at different locations. The approach is intrinsically efficient because, contrary to prior work, it relies neither on source separation, nor on mon…
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…
Wavelet Attribution Method (WAM) improves feature attribution for deep models.
Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles, this paper aims to explore their potentials towards mitigating adversarial inpu…
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…
Generative Adversarial Networks (GANs) have become exceedingly popular in a wide range of data-driven research fields, due in part to their success in image generation. Their ability to generate new samples, often from only a small amount of input data, makes them an exciting research tool in areas with limited data re…
Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data. In this paper, we propose using a cycle-consistent adversarial network (CycleGAN) for nonparallel data-based VC train…
Two-stream model recognizes affect from audio and video.
Improved deep CNNs for ASC by optimizing receptive field size.
An audiovisual speaker conversion method is presented for simultaneously transforming the facial expressions and voice of a source speaker into those of a target speaker. Transforming the facial and acoustic features together makes it possible for the converted voice and facial expressions to be highly correlated and f…
The problem of identifying voice commands has always been a challenge due to the presence of noise and variability in speed, pitch, etc. We will compare the efficacies of several neural network architectures for the speech recognition problem. In particular, we will build a model to determine whether a one second audio…
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…
Improves sampling speed of ARM models without losing accuracy.
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can be constructed by imperceptibly modifying images to cause misclassification, and…
Develops deep NMF models using β-divergences for feature extraction.
Deep audio prior uses neural networks to solve audio problems without data.
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…
Mapping states to actions in deep reinforcement learning is mainly based on visual information. The commonly used approach for dealing with visual information is to extract pixels from images and use them as state representation for reinforcement learning agent. But, any vision only agent is handicapped by not being ab…
Nowadays, a lot of scientific efforts are concentrated on the diagnosis of Alzheimer's Disease (AD) applying deep learning methods to neuroimaging data. Even for 2017, there were published more than a hundred papers dedicated to AD diagnosis, whereas only a few works considered a problem of mild cognitive impairments (…
Paper finds universal speech command perturbations that fool models.
This paper proposes a new method for efficient data compression using Bayesian neural networks.
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…