Related papers: Efficient Keyword Spotting by capturing long-range…

A major challenge to the problem of community question answering is the lexical and semantic gap between the sentence representations. Some solutions to minimize this gap includes the introduction of extra parameters to deep models or…

Success of deep learning techniques have renewed the interest in development of dialogue systems. However, current systems struggle to have consistent long term conversations with the users and fail to build rapport. Topic spotting, the…

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting…

This paper proposes a task-agnostic discovery layer for multivariate time series that constructs a relational hypothesis graph over entities without assuming linearity, stationarity, or a downstream objective. The method learns window-level…

Keyword Spotting plays a critical role in enabling hands-free interaction for battery-powered edge devices. Few-Shot Keyword Spotting (FS-KWS) addresses the scalability and adaptability challenges of traditional systems by enabling…

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…

In this paper we present a deep learning architecture for extracting word embeddings for visual speech recognition. The embeddings summarize the information of the mouth region that is relevant to the problem of word recognition, while…

In this work, we extend our previously proposed offline SpatialNet for long-term streaming multichannel speech enhancement in both static and moving speaker scenarios. SpatialNet exploits spatial information, such as the spatial/steering…

The evolution of Vision Transformers has led to their widespread adaptation to different domains. Despite large-scale success, there remain significant challenges including their reliance on extensive computational and memory resources for…

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

Modeling human conversations is the essence for building satisfying chat-bots with multi-turn dialog ability. Conversation modeling will notably benefit from domain knowledge since the relationships between sentences can be clarified due to…

Lipreading is the task of decoding text from the movement of a speaker's mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction. More recent deep lipreading approaches are…

Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented…

Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks. Yet neither stacks of convolutional operations to enlarge receptive fields nor recent…

Modelling various spatio-temporal dependencies is the key to recognising human actions in skeleton sequences. Most existing methods excessively relied on the design of traversal rules or graph topologies to draw the dependencies of the…

In order to successfully perform tasks specified by natural language instructions, an artificial agent operating in a visual world needs to map words, concepts, and actions from the instruction to visual elements in its environment. This…

Spatio-temporal prediction is a pivotal task with broad applications in traffic management, climate monitoring, energy scheduling, etc. However, existing methodologies often struggle to balance model expressiveness and computational…

We present a novel conversational-context aware end-to-end speech recognizer based on a gated neural network that incorporates conversational-context/word/speech embeddings. Unlike conventional speech recognition models, our model learns…

The goal of language modeling techniques is to capture the statistical and structural properties of natural languages from training corpora. This task typically involves the learning of short range dependencies, which generally model the…

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…