Related papers: Beyond Performance Plateaus: A Comprehensive Study…

One key aspect differentiating data-driven single- and multi-channel speech enhancement and dereverberation methods is that both the problem formulation and complexity of the solutions are considerably more challenging in the latter case.…

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

Recent research on speech enhancement (SE) has seen the emergence of deep-learning-based methods. It is still a challenging task to determine the effective ways to increase the generalizability of SE under diverse test conditions. In this…

This paper studies the Speech Enhancement based on Deep Neural Networks. The proposed architecture gradually follows the signal transformation during enhancement by means of a visualization probe at each network block. Alongside the…

Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable performance without increasing per-token compute. However, can MoEs surpass dense architectures under strictly equal resource constraints --…

Speech Foundation Models have gained significant attention recently. Prior works have shown that the fusion of representations from multiple layers of the same model or the fusion of multiple models can improve performance on downstream…

Speech enhancement (SE) based on diffusion probabilistic models has exhibited impressive performance, while requiring a relatively high number of function evaluations (NFE). Recently, SE based on flow matching has been proposed, which…

This survey paper provides a comprehensive overview of the recent advancements and challenges in applying large language models to the field of audio signal processing. Audio processing, with its diverse signal representations and a wide…

With the recent surge of video conferencing tools usage, providing high-quality speech signals and accurate captions have become essential to conduct day-to-day business or connect with friends and families. Single-channel personalized…

Slot filling is a crucial subtask in spoken language understanding (SLU), traditionally implemented as a cascade of speech recognition followed by one or more natural language understanding (NLU) components. The recent advent of…

Large-scale pre-trained self-supervised learning (SSL) models have shown remarkable advancements in speech-related tasks. However, the utilization of these models in complex multi-talker scenarios, such as extracting a target speaker in a…

Speech emotion recognition (SER) is an important aspect of effective human-robot collaboration and received a lot of attention from the research community. For example, many neural network-based architectures were proposed recently and…

The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language…

Deep learning models are widely used nowadays for their reliability in performing various tasks. However, they do not typically provide the reasoning behind their decision, which is a significant drawback, particularly for more sensitive…

We revisit continual pre-training for large language models and argue that progress now depends more on scaling the right structure than on scaling parameters alone. We introduce SCALE, a width upscaling architecture that inserts…

Learning representations of well-trained neural network models holds the promise to provide an understanding of the inner workings of those models. However, previous work has either faced limitations when processing larger networks or was…

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…

Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…

Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in…