Related papers: Pruning-aware Loss Functions for STOI-Optimized Pr…

With the rapid expansion of large language models (LLMs), the demand for memory and computational resources has grown significantly. Recent advances in LLM pruning aim to reduce the size and computational cost of these models. However,…

Deep learning has celebrated resounding successes in many application areas of relevance to the Internet of Things (IoT), such as computer vision and machine listening. These technologies must ultimately be brought directly to the edge to…

Recent audio-language models have shown impressive performance across a wide range of audio tasks and are increasingly capable of handling long audio inputs. However, the computing costs in these models heavily depend on sequence length,…

Brain Computer/Machine Interfaces (BCI/BMIs) have substantial potential for enhancing the lives of disabled individuals by restoring functionalities of missing body parts or allowing paralyzed individuals to regain speech and other motor…

Model pruning is an effective approach for compressing large language models (LLMs). However, this process often leads to significant degradation of model capabilities. While post-training techniques such as instruction tuning are commonly…

Massive MIMO systems rely on accurate Channel State Information (CSI) feedback to enable high-gain beam-forming. However, the feedback overhead scales linearly with the number of antennas, presenting a major bottleneck. While recent deep…

This dissertation covers a single-processor approach to the speech processing pipeline of bilateral Cochlear Implants (CIs). The use of only a single processor to provide binaural stimulation signals overcomes the synchronization problem,…

Dynamic head pruning in Vision Transformers (ViTs) improves efficiency by removing redundant attention heads, but existing pruning policies are often difficult to interpret and control. In this work, we propose a novel framework by…

Deep learning models have become increasingly popular for a wide range of applications, including computer vision, natural language processing, and speech recognition. However, these models typically require large amounts of computational…

Self-supervised pre-trained models such as Wav2vec2, Hubert, and WavLM have been shown to significantly improve many speech tasks. However, their large memory and strong computational requirements hinder their industrial applicability.…

Explicit channel state information at the transmitter side is helpful to improve downlink precoding performance for multi-user MIMO systems. In order to reduce feedback signalling overhead, compression of Channel State Information (CSI) is…

Pruning is an effective method to reduce the memory footprint and FLOPs associated with neural network models. However, existing structured-pruning methods often result in significant accuracy degradation for moderate pruning levels. To…

Efficient channel state information (CSI) compression at the user equipment plays a key role in enabling accurate channel reconstruction and precoder design in massive multiple-input multiple-output systems. A key challenge lies in…

Pruning is a popular technique for reducing the model size and computational cost of convolutional neural networks (CNNs). However, a slow retraining or fine-tuning procedure is often required to recover the accuracy loss caused by pruning.…

Speech intelligibility assessment is essential for many speech-related applications. However, most objective intelligibility metrics are intrusive, as they require clean reference speech in addition to the degraded or processed signal for…

Attempts to develop speech enhancement algorithms with improved speech intelligibility for cochlear implant (CI) users have met with limited success. To improve speech enhancement methods for CI users, we propose to perform speech…

Noise reduction is an important part of modern hearing aids and is included in most commercially available devices. Deep learning-based state-of-the-art algorithms, however, either do not consider real-time and frequency resolution…

Motivated by the issue of inaccurate channel state information (CSI) at the base station (BS), which is commonly due to feedback/processing delays and compression problems, in this paper, we introduce a scalable idea of adopting artificial…

The recent paradigm shift to large-scale foundation models has brought about a new era for deep learning that, while has found great success in practice, has also been plagued by prohibitively expensive costs in terms of high memory…

This paper proposes neural networks for compensating sensorineural hearing loss. The aim of the hearing loss compensation task is to transform a speech signal to increase speech intelligibility after further processing by a person with a…