Related papers: Speech enhancement with weakly labelled data from …

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

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…

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition…

While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural…

This work considers training neural networks for speaker recognition with a much smaller dataset size compared to contemporary work. We artificially restrict the amount of data by proposing three subsets of the popular VoxCeleb2 dataset.…

Audio DeepFakes are utterances generated with the use of deep neural networks. They are highly misleading and pose a threat due to use in fake news, impersonation, or extortion. In this work, we focus on increasing accessibility to the…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Building inclusive speech recognition systems is a crucial step towards developing technologies that speakers of all language varieties can use. Therefore, ASR systems must work for everybody independently of the way they speak. To…

The explosion of available speech data and new speaker modeling methods based on deep neural networks (DNN) have given the ability to develop more robust speaker recognition systems. Among DNN speaker modelling techniques, x-vector system…

Noise robustness is a key aspect of successful speech applications. Speech enhancement (SE) has been investigated to improve automatic speech recognition accuracy; however, its effectiveness for keyword spotting (KWS) is still…

In real acoustic environment, speech enhancement is an arduous task to improve the quality and intelligibility of speech interfered by background noise and reverberation. Over the past years, deep learning has shown great potential on…

Quality and intelligibility of speech signals are degraded under additive background noise which is a critical problem for hearing aid and cochlear implant users. Motivated to address this problem, we propose a novel speech enhancement…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task 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…

This paper proposes SEFGAN, a Deep Neural Network (DNN) combining maximum likelihood training and Generative Adversarial Networks (GANs) for efficient speech enhancement (SE). For this, a DNN is trained to synthesize the enhanced speech…

Noisy situations cause huge problems for suffers of hearing loss as hearing aids often make the signal more audible but do not always restore the intelligibility. In noisy settings, humans routinely exploit the audio-visual (AV) nature of…

Personalized speech enhancement (PSE) methods typically rely on pre-trained speaker verification models or self-designed speaker encoders to extract target speaker clues, guiding the PSE model in isolating the desired speech. However, these…