Search Results for author:
Found 33 papers, 19 papers with code
Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning
Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment.
Adversarial Representation Learning for Robust Privacy Preservation in Audio
In this study, we propose a novel adversarial training method for learning representations of audio recordings that effectively prevents the detection of speech activity from the latent features of the recordings.
Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network
Automatic estimation of domestic activities from audio can be used to solve many problems, such as reducing the labor cost for nursing the elderly people.
Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering
Audio question answering (AQA) is a multimodal translation task where a system analyzes an audio signal and a natural language question, to generate a desirable natural language answer.
Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
Having attracted attention only recently, very few works on AAC study the performance of existing pre-trained audio and natural language processing resources.
Unsupervised Audio-Caption Aligning Learns Correspondences between Individual Sound Events and Textual Phrases
We investigate unsupervised learning of correspondences between sound events and textual phrases through aligning audio clips with textual captions describing the content of a whole audio clip.
Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations
Although these factors play a well-understood role in the performance of ASC models, most works report single evaluation metrics taking into account all different strata of a particular dataset.
Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach
In our scenario, a pre-optimized AAC method is used for some unseen general audio signals and can update its parameters in order to adapt to the new information, given a new reference caption.
Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit
Researchers have recently started to study how the emotional speech heard by young infants can affect their developmental outcomes.
Enriched Music Representations with Multiple Cross-modal Contrastive Learning
Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information.
Learning Contextual Tag Embeddings for Cross-Modal Alignment of Audio and Tags
In this work we propose a method for learning audio representations using an audio autoencoder (AAE), a general word embeddings model (WEM), and a multi-head self-attention (MHA) mechanism.
WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information
Automated audio captioning (AAC) is a novel task, where a method takes as an input an audio sample and outputs a textual description (i. e. a caption) of its contents.
Conditioned Time-Dilated Convolutions for Sound Event Detection
Sound event detection (SED) is the task of identifying sound events along with their onset and offset times.
Multi-task Regularization Based on Infrequent Classes for Audio Captioning
Audio captioning is a multi-modal task, focusing on using natural language for describing the contents of general audio.
Revisiting Representation Learning for Singing Voice Separation with Sinkhorn Distances
In this work we present a method for unsupervised learning of audio representations, focused on the task of singing voice separation.
Sound Audio and Speech Processing
Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation
We focus on singing voice separation, employing an RNN architecture, and we replace the RNNs with DWS convolutions (DWS-CNNs).
Temporal Sub-sampling of Audio Feature Sequences for Automated Audio Captioning
In this work we present an approach that focuses on explicitly taking advantage of this difference of lengths between sequences, by applying a temporal sub-sampling to the audio input sequence.
COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations
Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features.
Unsupervised Interpretable Representation Learning for Singing Voice Separation
In this work, we present a method for learning interpretable music signal representations directly from waveform signals.
Sound Event Detection with Depthwise Separable and Dilated Convolutions
The number of the channels of the CNNs and size of the weight matrices of the RNNs have a direct effect on the total amount of parameters of the SED method, which is to a couple of millions.
Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters
The application of the low-bit quantization allows a 50% reduction of the DNN memory footprint while the STOI performance drops only by 2. 7%.
Clotho: An Audio Captioning Dataset
Audio captioning is the novel task of general audio content description using free text.
Crowdsourcing a Dataset of Audio Captions
In this paper we present a three steps based framework for crowdsourcing an audio captioning dataset, based on concepts and practises followed for the creation of widely used image captioning and machine translations datasets.
Sound Audio and Speech Processing
Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling
On the contrary, with our method there is a decrease of 4% at F1 score and an increase of 7% at ER for the TUT-SED Synthetic 2016 dataset.
Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification
A challenging problem in deep learning-based machine listening field is the degradation of the performance when using data from unseen conditions.
Examining the Mapping Functions of Denoising Autoencoders in Singing Voice Separation
We examine the mapping functions of neural networks based on the denoising autoencoder (DAE) model that are conditioned on the mixture magnitude spectra.
Unsupervised adversarial domain adaptation for acoustic scene classification
A general problem in acoustic scene classification task is the mismatched conditions between training and testing data, which significantly reduces the performance of the developed methods on classification accuracy.
MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning based methods.
Sound Audio and Speech Processing
Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask
Singing voice separation based on deep learning relies on the usage of time-frequency masking.
Sound Audio and Speech Processing
Automated Audio Captioning with Recurrent Neural Networks
The encoder is a multi-layered, bi-directional gated recurrent unit (GRU) and the decoder a multi-layered GRU with a classification layer connected to the last GRU of the decoder.
Stacked Convolutional and Recurrent Neural Networks for Bird Audio Detection
This paper studies the detection of bird calls in audio segments using stacked convolutional and recurrent neural networks.
Stacked Convolutional and Recurrent Neural Networks for Music Emotion Recognition
This paper studies the emotion recognition from musical tracks in the 2-dimensional valence-arousal (V-A) emotional space.
Convolutional Recurrent Neural Networks for Bird Audio Detection
Bird sounds possess distinctive spectral structure which may exhibit small shifts in spectrum depending on the bird species and environmental conditions.
