Related papers: End-To-End Deep Learning-based Adaptation Control …

In recent years, neural networks (NNs) have been widely applied in acoustic echo cancellation (AEC). However, existing approaches struggle to meet real-world low-latency and computational requirements while maintaining performance. To…

It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public address systems. To…

End-to-end speaker diarization approaches have shown exceptional performance over the traditional modular approaches. To further improve the performance of the end-to-end speaker diarization for real speech recordings, recently works have…

We present a deep neural network (DNN) acoustic model that includes parametrised and differentiable pooling operators. Unsupervised acoustic model adaptation is cast as the problem of updating the decision boundaries implemented by each…

The integration of artificial intelligence into hearing assistance marks a paradigm shift from traditional amplification-based systems to intelligent, context-aware audio processing. This systematic literature review evaluates advances in…

Self-supervised learning has emerged as a key approach for learning generic representations from speech data. Despite promising results in downstream tasks such as speech recognition, speaker verification, and emotion recognition, a…

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

Speech enhancement in ad-hoc microphone arrays is often hindered by the asynchronization of the devices composing the microphone array. Asynchronization comes from sampling time offset and sampling rate offset which inevitably occur when…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

One of the main difficulties in echo cancellation is the fact that the learning rate needs to vary according to conditions such as double-talk and echo path change. In this paper we propose a new method of varying the learning rate of a…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

We propose a novel Neural Steering technique that adapts the target area of a spatial-aware multi-microphone sound source separation algorithm during inference without the necessity of retraining the deep neural network (DNN). To achieve…

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains…

We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings. End-to-end diarization models have the advantage of handling speaker overlap and enabling straightforward handling of…

Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design decisions including network architecture, size, and training…

Enhancing noisy speech is an important task to restore its quality and to improve its intelligibility. In traditional non-machine-learning (ML) based approaches the parameters required for noise reduction are estimated blindly from the…

End-to-end learning treats the entire system as a whole adaptable black box, which, if sufficient data are available, may learn a system that works very well for the target task. This principle has recently been applied to several prototype…

Deep complex convolution recurrent network (DCCRN), which extends CRN with complex structure, has achieved superior performance in MOS evaluation in Interspeech 2020 deep noise suppression challenge (DNS2020). This paper further extends…

Recognition of overlapped speech has been a highly challenging task to date. State-of-the-art multi-channel speech separation system are becoming increasingly complex and expensive for practical applications. To this end, low-bit neural…

When using ultrasound video as input, Deep Neural Network-based Silent Speech Interfaces usually rely on the whole image to estimate the spectral parameters required for the speech synthesis step. Although this approach is quite…