Related papers: Trainable Frontend For Robust and Far-Field Keywor…

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces…

Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial…

Recent work has shown the impact of adversarial machine learning on deep neural networks (DNNs) developed for Radio Frequency Machine Learning (RFML) applications. While these attacks have been shown to be successful in disrupting the…

In this study, we revisit key training strategies in machine learning often overlooked in favor of deeper architectures. Specifically, we explore balancing strategies, activation functions, and fine-tuning techniques to enhance speech…

Acoustic echo cancellation (AEC) plays an important role in the full-duplex speech communication as well as the front-end speech enhancement for recognition in the conditions when the loudspeaker plays back. In this paper, we present an…

Many of the challenges facing today's reinforcement learning (RL) algorithms, such as robustness, generalization, transfer, and computational efficiency are closely related to compression. Prior work has convincingly argued why minimizing…

Using supporting backchannel (BC) cues can make human-computer interaction more social. BCs provide a feedback from the listener to the speaker indicating to the speaker that he is still listened to. BCs can be expressed in different ways,…

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution…

Convolutional Neural Networks (CNNs) are well-known for their vulnerability to adversarial attacks, posing significant security concerns. In response to these threats, various defense methods have emerged to bolster the model's robustness.…

Recent advances in machine learning, wireless communication, and mobile hardware technologies promisingly enable federated learning (FL) over massive mobile edge devices, which opens new horizons for numerous intelligent mobile…

Deep learning accelerators efficiently train over vast and growing amounts of data, placing a newfound burden on commodity networks and storage devices. A common approach to conserve bandwidth involves resizing or compressing data prior to…

Speech Emotion Recognition (SER) is fundamental to affective computing and human-computer interaction, yet existing models struggle to generalize across diverse acoustic conditions. While Contrastive Language-Audio Pretraining (CLAP)…

Deep neural networks (DNNs) have shown remarkable performance in a variety of domains such as computer vision, speech recognition, or natural language processing. Recently they also have been applied to various software engineering tasks,…

Deploying a well-optimized pre-trained speaker recognition model in a new domain often leads to a significant decline in performance. While fine-tuning is a commonly employed solution, it demands ample adaptation data and suffers from…

In this paper, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker recognition system. We started with augmenting the Fisher database with…

We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these…

Acoustic echo cancellation (AEC) is an important speech signal processing technology that can remove echoes from microphone signals to enable natural-sounding full-duplex speech communication. While single-channel AEC is widely adopted,…

Recent years have witnessed a boom in self-supervised learning (SSL) in various areas including speech processing. Speech based SSL models present promising performance in a range of speech related tasks. However, the training of SSL models…

We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…