Related papers: Neural Analysis and Synthesis: Reconstructing Spee…

We propose a novel neural waveform compression method to catalyze emerging speech semantic communications. By introducing nonlinear transform and variational modeling, we effectively capture the dependencies within speech frames and…

This paper introduces an innovative method for reducing the computational complexity of deep neural networks in real-time speech enhancement on resource-constrained devices. The proposed approach utilizes a two-stage processing framework,…

We propose a computational model of speech production combining a pre-trained neural articulatory synthesizer able to reproduce complex speech stimuli from a limited set of interpretable articulatory parameters, a DNN-based internal forward…

We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from trained speech models without full retraining. This has…

Recent advances in unsupervised learning have highlighted the possibility of learning to reconstruct signals from noisy and incomplete linear measurements alone. These methods play a key role in medical and scientific imaging and sensing,…

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adversarial Networks (GANs) have increasingly been used in…

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual…

Speech is a means of communication which relies on both audio and visual information. The absence of one modality can often lead to confusion or misinterpretation of information. In this paper we present an end-to-end temporal model capable…

With the huge technological advances introduced by deep learning in audio & speech processing, many novel synthetic speech techniques achieved incredible realistic results. As these methods generate realistic fake human voices, they can be…

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Speech data collected in real-world scenarios often encounters two issues. First, multiple sources may exist simultaneously, and the number of sources may vary with time. Second, the existence of background noise in recording is inevitable.…

We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice…

Faced with the scarcity of clean label data in real scenarios, seismic denoising methods based on supervised learning (SL) often encounter performance limitations. Specifically, when a model trained on synthetic data is directly applied to…

Target speech separation is the process of filtering a certain speaker's voice out of speech mixtures according to the additional speaker identity information provided. Recent works have made considerable improvement by processing signals…

Articulatory information has been shown to be effective in improving the performance of HMM-based and DNN-based text-to-speech synthesis. Speech synthesis research focuses traditionally on text-to-speech conversion, when the input is text…

Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…

Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is…

Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging. Strong speech enhancement front-ends are available, however, they typically require that the ASR model is retrained to cope with…

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There…