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

Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently,…

Audio compression has become one of the basic multimedia technologies. Choosing an efficient compression scheme that is capable of preserving the signal quality while providing a high compression ratio is desirable in the different…

This paper studies optimization proxies, machine learning (ML) models trained to efficiently predict optimal solutions for AC Optimal Power Flow (ACOPF) problems. While promising, optimization proxy performance heavily depends on training…

Existing Vision-Language-Action (VLA) models can be broadly categorized into diffusion-based and auto-regressive (AR) approaches: diffusion models capture continuous action distributions but rely on computationally heavy iterative…

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…

Transformer-based large-scale pre-trained models achieve great success. Fine-tuning is the standard practice for leveraging these models in downstream tasks. Among the fine-tuning methods, adapter-tuning provides a parameter-efficient…

Many pre-trained language models (PLMs) exhibit suboptimal performance on mid- and low-resource languages, largely due to limited exposure to these languages during pre-training. A common strategy to address this is to introduce new tokens…

Echo cancellation and noise reduction are essential for full-duplex communication, yet most existing neural networks have high computational costs and are inflexible in tuning model complexity. In this paper, we introduce time-frequency…

Subsequence matching has appeared to be an ideal approach for solving many problems related to the fields of data mining and similarity retrieval. It has been shown that almost any data class (audio, image, biometrics, signals) is or can be…

This work presents a novel probabilistic interpretation of Slow Feature Analysis (SFA) through the lens of variational inference. Unlike prior formulations that recover linear SFA from Gaussian state-space models with linear emissions, this…

Long-context autoregressive decoding remains expensive because each decoding step must repeatedly process a growing history. We observe a consistent pattern during decoding: within a sentence, and more generally within a short semantically…

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the…

Audio coding is an essential module in the real-time communication system. Neural audio codecs can compress audio samples with a low bitrate due to the strong modeling and generative capabilities of deep neural networks. To address the poor…

This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consideration. Specifically, we propose to use generative learning…

Self-supervised speech representations have been shown to be effective in a variety of speech applications. However, existing representation learning methods generally rely on the autoregressive model and/or observed global dependencies…

We consider the problem of learning a low-dimensional signal model from a collection of training samples. The mainstream approach would be to learn an overcomplete dictionary to provide good approximations of the training samples using…

Factorization Machines (FM), a general predictor that can efficiently model feature interactions in linear time, was primarily proposed for collaborative recommendation and have been broadly used for regression, classification and ranking…

Fast Fourier convolution (FFC) is the recently proposed neural operator showing promising performance in several computer vision problems. The FFC operator allows employing large receptive field operations within early layers of the neural…

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…