Related papers: Wave-Based Semantic Memory with Resonance-Based Re…

Embedding-based neural retrieval is a prevalent approach to address the semantic gap problem which often arises in product search on tail queries. In contrast, popular queries typically lack context and have a broad intent where additional…

Vector search (VS) has become a fundamental component in multimodal data management, enabling core functionalities such as image, video, and code retrieval. As vector data scales rapidly, VS faces growing challenges in balancing search,…

Speech recognition from raw waveform involves learning the spectral decomposition of the signal in the first layer of the neural acoustic model using a convolution layer. In this work, we propose a raw waveform convolutional filter learning…

A new method for the study of resonant behavior - using wave-packet dynamics - is presented, based on the powerful window operator technique. The method is illustrated and quantified by application to the astrophysically-important example…

An autoassociative memory model is a function that, given a set of data points, takes as input an arbitrary vector and outputs the most similar data point from the memorized set. However, popular memory models fail to retrieve images even…

Learned sparse representations form an attractive class of contextual embeddings for text retrieval. That is so because they are effective models of relevance and are interpretable by design. Despite their apparent compatibility with…

Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retrieval-augmented generation (RAG), which stores verbatim…

Spatio-temporal signals arising from event-driven biological processes, such as surface electromyography (sEMG), exhibit asynchronous and highly structured activation patterns that are challenging to model using conventional discrete or…

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…

Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval and recognition tasks,…

Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity…

Our brains encode many features of the sensory world into memories: we can sing along with songs we have heard before, interpret spoken and written language composed of words we have learned, and recognize faces and objects. Where are these…

Convolutional Neural Network(CNN) has been widely used for image recognition with great success. However, there are a number of limitations of the current CNN based image recognition paradigm. First, the receptive field of CNN is generally…

Learning a high-dimensional dense representation for vocabulary terms, also known as a word embedding, has recently attracted much attention in natural language processing and information retrieval tasks. The embedding vectors are typically…

Previous research has looked into ways to improve speech emotion recognition (SER) by utilizing both acoustic and linguistic cues of speech. However, the potential association between state-of-the-art ASR models and the SER task has yet to…

Analogical Reasoning problems challenge both connectionist and symbolic AI systems as these entail a combination of background knowledge, reasoning and pattern recognition. While symbolic systems ingest explicit domain knowledge and perform…

Most of the deep learning based speech enhancement (SE) methods rely on estimating the magnitude spectrum of the clean speech signal from the observed noisy speech signal, either by magnitude spectral masking or regression. These methods…

Knowledge workers face an ever increasing flood of information in their daily lives. To counter this and provide better support for information management and knowledge work in general, we have been investigating solutions inspired by human…

Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in…