Related papers: Semantically Optimized End-to-End Learning for Pos…

End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling,…

Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time. Neural segmental models are segmental models that…

Semantic communication has emerged as a promising technology to break the Shannon limit by extracting the meaning of source data and sending relevant semantic information only. However, some mobile devices may have limited computation and…

Learning token embeddings based on token co-occurrence statistics has proven effective for both pre-training and fine-tuning in natural language processing. However, recent studies have pointed out that the distribution of learned…

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Recent works showed that end-to-end neural approaches tend to become very popular for spoken language understanding (SLU). Through the term end-to-end, one considers the use of a single model optimized to extract semantic information…

We propose semantic communication over wireless channels for various modalities, e.g., text and images, in a task-oriented communications setup where the task is classification. We present two approaches based on memory and learning. Both…

End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired…

Sentence embeddings are crucial in measuring semantic similarity. Most recent studies employed large language models (LLMs) to learn sentence embeddings. Existing LLMs mainly adopted autoregressive architecture without explicit backward…

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

As wireless networks evolve towards high mobility and providing better support for connected vehicles, a number of new challenges arise due to the resulting high dynamics in vehicular environments and thus motive rethinking of traditional…

Semantic communication is considered the future of mobile communication, which aims to transmit data beyond Shannon's theorem of communications by transmitting the semantic meaning of the data rather than the bit-by-bit reconstruction of…

Deep learning is a potential paradigm changer for the design of wireless communications systems (WCS), from conventional handcrafted schemes based on sophisticated mathematical models with assumptions to autonomous schemes based on the…

With the development and the increasing interests in ML/DL fields, companies are eager to apply Machine Learning/Deep Learning approaches to increase service quality and customer experience. Federated Learning was implemented as an…

Innovation in the physical layer of communication systems has traditionally been achieved by breaking down the transceivers into sets of processing blocks, each optimized independently based on mathematical models. Conversely, deep learning…

Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…

Physics-based models often involve large systems of parametrized partial differential equations, where design parameters control various properties. However, high-fidelity simulations of such systems on large domains or with high grid…

Recent applications of deep learning to navigation have generated end-to-end navigation solutions whereby visual sensor input is mapped to control signals or to motion primitives. The resulting visual navigation strategies work very well at…

Human drivers adeptly navigate complex scenarios by utilizing rich attentional semantics, but the current autonomous systems struggle to replicate this ability, as they often lose critical semantic information when converting 2D…

Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks.…