Bayesian Gaussian Processes improve exoplanet transit and Hubble constant inference.
problem Improving exoplanet transit and Hubble constant inference using Bayesian Gaussian Processes.
method Kernel-, mean- and noise-marginalised Gaussian Processes with evidence-based model comparison and transdimensional sampling.
result Inferred Hubble constant H0 values from cosmic chronometers, baryon acoustic oscillations and combined datasets are 66±6kms−1Mpc−1, 67±10kms−1Mpc−1 and 69±6kms−1Mpc−1, respectively. Physics-informed neural networks improve baryonic predictions from dark matter simulations.
problem Recreating hydrodynamic simulations from dark matter requires expensive and time-consuming computations.
method Combining neural network architectures with physical constraints and using Kullback-Leibler divergence for prediction comparison.
result Improved accuracy of baryonic predictions based on dark matter halo properties, successful recovery of the metallicity relation, and preserved scatter.
Hybrid model speeds up galaxy simulations by incorporating baryonic properties.
problem Inaccurate baryonic properties in dark matter-only simulations.
method Combining analytic models and machine learning for faster, more accurate simulations.
result Hybrid model outperforms machine learning alone for some baryonic properties.
We show that the baryon number of N=2 supersymmetric QCD can be twisted in order to couple the topological field theory of non-abelian monopoles to Spinc-structures. To motivate the construction, we also consider some aspects of the twisting procedure as a gauging of global currents in two and four dimensions, in pa…
Running hydrodynamical simulations to produce mock data of large-scale structure and baryonic probes, such as the thermal Sunyaev-Zeldovich (tSZ) effect, at cosmological scales is computationally challenging. We propose to leverage the expressive power of deep generative models to find an effective description of the l…
Paper aims to find joint representation between vocal tract geometry and speech sound acoustics.
problem Finding a joint latent representation between articulatory and acoustic domains for vowel sounds.
method Invertible neural network models, convolutional autoencoder, normalizing flows, semi-supervised learning.
result Satisfactory performance in articulatory-to-acoustic and acoustic-to-articulatory mapping.
Study shows integrating acoustic features in financial forecasting models can degrade performance.
problem Predicting stock market volatility from corporate earnings calls using speech features.
method Empirical investigation of acoustic feature extraction in teleconference environments using a two-stream late-fusion architecture.
result Integrating acoustic features via late fusion significantly degraded performance, reducing recall to 47.08%.
In this paper we demonstrate predicting electroencephalograpgy (EEG) features from acoustic features using recurrent neural network (RNN) based regression model and generative adversarial network (GAN). We predict various types of EEG features from acoustic features. We compare our results with the previously studied p…
We introduce the new task of Acoustic Question Answering (AQA) to promote research in acoustic reasoning. The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds. The kind of relational questions …
Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly co…
We present a supervised neural network model for polyphonic piano music transcription. The architecture of the proposed model is analogous to speech recognition systems and comprises an acoustic model and a music language model. The acoustic model is a neural network used for estimating the probabilities of pitches in …
This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure: first the model learns the notion of acoustic units from the labelled data and …
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to voco…
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…
This paper introduces a model of environmental acoustic scenes which adopts a morphological approach by ab-stracting temporal structures of acoustic scenes. To demonstrate its potential, this model is employed to evaluate the performance of a large set of acoustic events detection systems. This model allows us to expli…
New construction reveals SU(2)-flavor fields in heterotic M5-brane model.
problem Tackles the emergence of SU(2)-flavor fields in heterotic M5-brane models.
method Classifies super-exceptional field content and works out interactions.
result SU(2)xU(1)-valued scalar and vector fields emerge from probe M2- and M5-branes.
Acoustic Neighbor Embeddings map speech and text to fixed dimensions for phonetic confusability.
problem Mapping speech and text to fixed dimensions for phonetic confusability.
method Adapting SNE to sequential inputs, training two encoder neural networks.
result More accurate results with low-dimensional embeddings in word recognition tasks.
A new oscillator measures trending behavior of financial instruments.
problem Detecting underlying deterministic components in financial market prices.
method Financial market geometry and tube oscillator derived from past history.
result Simple trading strategy based on tube oscillator leads to consistent positive returns.
We present a novel deep Recurrent Neural Network (RNN) model for acoustic modelling in Automatic Speech Recognition (ASR). We term our contribution as a TC-DNN-BLSTM-DNN model, the model combines a Deep Neural Network (DNN) with Time Convolution (TC), followed by a Bidirectional Long Short-Term Memory (BLSTM), and a fi…
Minimal vector fields on oscillator groups studied, with specific conditions for minimality.
problem Characterizing minimal left-invariant unit vector fields on oscillator groups.
method Analyzing structure constants and harmonic maps into the unit tangent bundle.
result Minimal vector fields defined by specific conditions on oscillator groups.
Study examines boundedness of oscillating singular integrals on specific Lie groups.
problem Investigating boundedness of oscillating singular integrals on Lie groups of polynomial growth.
method Presented kernel criteria in terms of sub-Riemannian structure and Fourier analysis.
result Extended classical oscillating conditions for boundedness of oscillating convolution operators.
Log-periodic oscillations have been used to predict price trends and crashes on financial markets. So far two types of log-periodic oscillations have been associated with the real markets. The first type are oscillations which accompany a rising market and which ends in a crash. The second type oscillations, called "an…
Environmental acoustic sensing involves the retrieval and processing of audio signals to better understand our surroundings. While large-scale acoustic data make manual analysis infeasible, they provide a suitable playground for machine learning approaches. Most existing machine learning techniques developed for enviro…
Geometric model explains music perception combining neuroscience and acoustics.
problem Rationalize and predict psycho-acoustic phenomena in music perception.
method Combining neuroscientific theories with acoustic observations, a geometric model of the space of all chords is created.
result The geometric model allows for rigorous studies of psychoacoustic quantities like roughness and harmonicity.
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic m…
Estimates box dimension of fractal interpolation surfaces using oscillation vectors.
problem Estimating the complexity of fractal interpolation surfaces.
method Defined vertical scaling matrices and used them to relate oscillation vectors of different levels.
result Obtained the box dimension of generalized affine fractal interpolation surfaces.
Acoustic word embeddings --- fixed-dimensional vector representations of arbitrary-length words --- have attracted increasing interest in query-by-example spoken term detection. Recently, on the fact that the orthography of text labels partly reflects the phonetic similarity between the words' pronunciation, a multi-vi…
Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes. In this work, we present a Convolutional Neural Network that is capable of classifying the vocalizations o…
Researchers classify lattices in a specific four-dimensional group.
problem Classifying lattices in the split oscillator group.
method Parametrizing and classifying lattices up to automorphisms of the ambient group.
result Commensurability classes of lattices correspond to real quadratic fields.
We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN…
We introduce the task of acoustic question answering (AQA) in the area of acoustic reasoning. In this task an agent learns to answer questions on the basis of acoustic context. In order to promote research in this area, we propose a data generation paradigm adapted from CLEVR (Johnson et al. 2017). We generate acoustic…
U-Net trained to recover acoustic interference striations from distorted data.
problem Recovering acoustic interference striations from distorted signals.
method Training a U-Net using a random mode-coupling matrix model to generate training data.
result U-Net successfully recovers AISs under various conditions.
In this paper, we propose a classification based glottal closure instants (GCI) detection from pathological acoustic speech signal, which finds many applications in vocal disorder analysis. Till date, GCI for pathological disorder is extracted from laryngeal (glottal source) signal recorded from Electroglottograph, a d…
Constructing a dataset for replay spoofing detection requires a physical process of playing an utterance and re-recording it, presenting a challenge to the collection of large-scale datasets. In this study, we propose a self-supervised framework for pretraining acoustic configurations using datasets published for other…
Improved ASR for English-isiZulu code-switched speech with semi-supervised training.
problem Improving ASR for code-switched speech between English and isiZulu.
method Semi-supervised training using automatic transcription of multilingual speech data.
result Semi-supervised training achieved significant WER reduction in ASR performance.
The Duffing oscillator's parameters are identified online using variational message passing.
problem Estimating parameters of a nonlinear Duffing oscillator in real-time.
method Variational message passing on a factor graph of the Duffing oscillator's generative model.
result The online inference procedure performs as well as offline methods.
New method linearizes nonlinear coupled oscillators on graphs.
problem Predicting global synchronization in nonlinear coupled oscillators on graphs.
method Latent dynamic filters learned through supervised matrix factorization.
result Latent dynamics filters enable effective prediction of global synchronization.
Improved multi-modal emotion recognition using deep learning.
problem Combining acoustic and text modalities for emotion recognition.
method Proposes a deep learning-based approach to fuse text and acoustic data using SincNet for acoustic features and parallel DCNN and Bi-RNN branches for text processing with cross attention.
result Achieves 3.5% improvement in weighted accuracy compared to existing methods.
Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices. The ability, however, to reliably identify vocalising animal species is…
The present paper introduces a majority orienting model in which the dealers' behavior changes based on the influence of the price to show the oscillation of stock price in the stock market. We show the oscillation of the price for the model by applying the van der Pol equation which is a deterministic approximation of…
The study derives generalization bounds for neural oscillators, improving their performance with regularization.
problem Quantifying the generalization capacities of neural oscillators.
method Using Rademacher complexity and squared Wasserstein-1 distances, the study derives theoretical upper PAC generalization bounds for neural oscillators.
result Theoretical bounds show polynomial growth in estimation errors with MLP size and time length, and regularization improves performance.
Study finds the spectrum of a cubic Dirac operator on specific oscillator group manifolds.
problem Determining the spectrum of a cubic Dirac operator on oscillator group manifolds.
method Explicit decomposition of the regular representation and calculation of eigenspaces.
result Explicit eigenspaces and spectrum of the cubic Dirac operator determined.
Study on black hole interiors with matter fields, showing oscillation condition impacts blow-up.
problem Examining Strong Cosmic Censorship in the presence of matter fields.
method Einstein equations coupled with charged/massive scalar fields, spherically symmetric data, relaxation rate analysis.
result Oscillation condition on event horizon determines whether matter fields blow up or not.
Traditional automatic speech recognition (ASR) systems often use an acoustic model (AM) built on handcrafted acoustic features, such as log Mel-filter bank (FBANK) values. Recent studies found that AMs with convolutional neural networks (CNNs) can directly use the raw waveform signal as input. Given sufficient training…
We study geometric quantization of the harmonic oscillator in terms of a singular real polarization given by fibres of the energy momentum map.
Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNNs). However, a limitation is the lack of synchronized audio, video, an…
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…
Improves speech recognition in noisy environments using robust acoustic models.
problem Adverse environments with significant mismatch between training and test conditions.
method Theoretical analysis of data augmentation as vicinal risk minimization, using mixture of Gaussians to incorporate robust inductive bias.
result Waveform-based approach shows 150% relative improvement in out-of-distribution generalization.