相关论文: Sparse, Efficient, and Semantic Mixture Invariant …

Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, and task-specific requirements, leading to "constrained"…

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…

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

The major driving force behind the immense success of deep learning models is the availability of large datasets along with their clean labels. Unfortunately, this is very difficult to obtain, which has motivated research on the training of…

Source separation involves the ill-posed problem of retrieving a set of source signals that have been observed through a mixing operator. Solving this problem requires prior knowledge, which is commonly incorporated by imposing regularity…

We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…

The separation of single-channel underwater acoustic signals is a challenging problem with practical significance. Few existing studies focus on the source separation problem with unknown numbers of signals, and how to evaluate the…

Data-driven speech enhancement employing deep neural networks (DNNs) can provide state-of-the-art performance even in the presence of non-stationary noise. During the training process, most of the speech enhancement neural networks are…

This paper introduces a novel framework designed to achieve a high compression ratio in Split Learning (SL) scenarios where resource-constrained devices are involved in large-scale model training. Our investigations demonstrate that…

Learning based methods are now ubiquitous for solving inverse problems, but their deployment in real-world applications is often hindered by the lack of ground truth references for training. Recent self-supervised learning strategies offer…

Semi-supervised learning techniques are gaining popularity due to their capability of building models that are effective, even when scarce amounts of labeled data are available. In this paper, we present a framework and specific tasks for…

Unsupervised blind source separation methods do not require a training phase and thus cannot suffer from a train-test mismatch, which is a common concern in neural network based source separation. The unsupervised techniques can be…

With the rise in interest of sparse neural networks, we study how neural network pruning with synthetic data leads to sparse networks with unique training properties. We find that distilled data, a synthetic summarization of the real data,…

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most…

Despite being robust to small amounts of label noise, convolutional neural networks trained with stochastic gradient methods have been shown to easily fit random labels. When there are a mixture of correct and mislabelled targets, networks…

Post-training Sparsity (PTS) is a recently emerged avenue that chases efficient network sparsity with limited data in need. Existing PTS methods, however, undergo significant performance degradation compared with traditional methods that…

Speech separation has been studied in time domain because of lower latency and higher performance compared to time-frequency domain. The masking-based method has been mostly used in time domain, and the other common method (mapping-based)…

We present a novel approach that improves the performance of reverberant speech separation. Our approach is based on an accurate geometric acoustic simulator (GAS) which generates realistic room impulse responses (RIRs) by modeling both…

The performance of single channel source separation algorithms has improved greatly in recent times with the development and deployment of neural networks. However, many such networks continue to operate on the magnitude spectrogram of a…

Multi-talker conversational speech processing has drawn many interests for various applications such as meeting transcription. Speech separation is often required to handle overlapped speech that is commonly observed in conversation.…