Related papers: Speech Disorder Classification Using Extended Fact…
Voice disorders are pathologies significantly affecting patient quality of life. However, non-invasive automated diagnosis of these pathologies is still under-explored, due to both a shortage of pathological voice data, and diversity of the…
In this paper, we present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are shared between the…
Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…
Existing work on automated hate speech detection typically focuses on binary classification or on differentiating among a small set of categories. In this paper, we propose a novel method on a fine-grained hate speech classification task,…
For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for…
This paper introduces a modified variational autoencoder (VAEs) that contains an additional neural network branch. The resulting branched VAE (BVAE) contributes a classification component based on the class labels to the total loss and…
Speech contains information that is clinically relevant to some diseases, which has the potential to be used for health assessment. Recent work shows an interest in applying deep learning algorithms, especially pretrained large speech…
In recent years, end-to-end approaches have made notable progress in addressing the challenge of speaker diarization, which involves segmenting and identifying speakers in multi-talker recordings. One such approach, Encoder-Decoder…
In this paper, a hierarchical attention network to generate utterance-level embeddings (H-vectors) for speaker identification is proposed. Since different parts of an utterance may have different contributions to speaker identities, the use…
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences. Distinct from existing VAE-based text generative models, SIVAE contains two…
Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…
This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…
Currently end-to-end deep learning based open-domain dialogue systems remain black box models, making it easy to generate irrelevant contents with data-driven models. Specifically, latent variables are highly entangled with different…
High-dimensional clinical data have become invaluable resources for genetic studies, due to their accessibility in biobank-scale datasets and the development of high performance modeling techniques especially using deep learning. Recent…
Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying causes of speech…
This paper introduces the Descriptive Variational Autoencoder (DVAE), an unsupervised and end-to-end trainable neural network for predicting vehicle trajectories that provides partial interpretability. The novel approach is based on the…
In recent years, speech emotion recognition (SER) has been used in wide ranging applications, from healthcare to the commercial sector. In addition to signal processing approaches, methods for SER now also use deep learning techniques which…
We propose a novel and theoretical model, blocked and hierarchical variational autoencoder (BHiVAE), to get better-disentangled representation. It is well known that information theory has an excellent explanatory meaning for the network,…
Speech enhancement significantly improves the clarity and intelligibility of speech in noisy environments, improving communication and listening experiences. In this paper, we introduce a novel pretraining feature-guided diffusion model…
Recently, variational autoencoder (VAE), a deep representation learning (DRL) model, has been used to perform speech enhancement (SE). However, to the best of our knowledge, current VAE-based SE methods only apply VAE to the model speech…