Related papers: Once-for-All Sequence Compression for Self-Supervi…

Attention mechanisms have achieved significant empirical success in multiple fields, but their underlying optimization objectives remain unclear yet. Moreover, the quadratic complexity of self-attention has become increasingly prohibitive.…

Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive successes on downstream tasks, we still have a limited…

Autoregressive models are widely used for tasks such as image and audio generation. The sampling process of these models, however, does not allow interruptions and cannot adapt to real-time computational resources. This challenge impedes…

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

We propose an efficient once-for-all budgeted pruning framework (OFARPruning) to find many compact network structures close to winner tickets in the early training stage considering the effect of input resolution during the pruning process.…

Feature compression is increasingly important for improving the efficiency of downstream tasks, especially in applications involving large-scale or multi-modal data. While existing methods typically rely on dedicated models for achieving…

Expanding on neural operators, we propose a novel framework for stochastic process learning across arbitrary domains. In particular, we develop operator flow matching (OFM) for learning stochastic process priors on function spaces. OFM…

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…

Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered…

In automatic speech recognition, subsampling is essential for tackling diverse scenarios. However, the inadequacy of a single subsampling rate to address various real-world situations often necessitates training and deploying multiple…

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…

The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the…

Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, we study six prompt compression…

Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint. For neural networks, prior methods, including those based on $\ell_1$…

We introduce a fast low-rank factorization-based framework for compressing large language models that enables rapid compression of billion-parameter models without retraining. Unlike existing factorization-based approaches that optimize…

Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order through masked diffusion framework, which progressively unmasks positions and allows arbitrary…

Neuromorphic computing, inspired by nervous systems, revolutionizes information processing with its focus on efficiency and low power consumption. Using sparse coding, this paradigm enhances processing efficiency, which is crucial for edge…

In the context of long-term video understanding with large multimodal models, many frameworks have been proposed. Although transformer-based visual compressors and memory-augmented approaches are often used to process long videos, they…

Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…

Constraints over finite sequences of variables are ubiquitous in sequencing and timetabling. Moreover, the wide variety of such constraints in practical applications led to general modelling techniques and generic propagation algorithms,…