Related papers: Running Conventional Automatic Speech Recognition …

The recent widespread adoption of Large Language Models (LLMs) and machine learning in general has sparked research interest in exploring the possibilities of deploying these models on smaller devices such as laptops and mobile phones. This…

The adoption of intelligent systems with Artificial Neural Networks (ANNs) embedded in hardware for real-time applications currently faces a growing demand in fields like the Internet of Things (IoT) and Machine to Machine (M2M). However,…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention's computation…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

The modern implementation of machine learning architectures faces significant challenges due to frequent data transfer between memory and processing units. In-memory computing, primarily through memristor-based analog computing, offers a…

This paper presents a comparative study aimed at optimizing Llama2 inference, a critical aspect of machine learning and natural language processing (NLP). We evaluate various programming languages and frameworks, including TensorFlow,…

We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture…

Memristor-based neural networks provide an exceptional energy-efficient platform for artificial intelligence (AI), presenting the possibility of self-powered operation when paired with energy harvesters. However, most memristor-based…

Long Short-Term memory (LSTM) architecture is a well-known approach for building recurrent neural networks (RNN) useful in sequential processing of data in application to natural language processing. The near-sensor hardware implementation…

Model architectures such as wav2vec 2.0 and HuBERT have been proposed to learn speech representations from audio waveforms in a self-supervised manner. When they are combined with downstream tasks such as keyword spotting and speaker…

The tunability of conductance states of various emerging non-volatile memristive devices emulates the plasticity of biological synapses, making it promising in the hardware realization of large-scale neuromorphic systems. The inference of…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents that need to be carefully selected and tuned. As a result the…

Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data, which can compromise evaluation metrics, raise privacy concerns, and limit…

Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term…

Emerging nanodevices such as resistive memories are being considered for hardware realizations of a variety of artificial neural networks (ANNs), including highly promising online variants of the learning approaches known as reservoir…

Large language models have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering. In this paper we extend the capabilities of LLMs by directly…

Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic…

Despite all the progress of semiconductor integrated circuit technology, the extreme complexity of the human cerebral cortex makes the hardware implementation of neuromorphic networks with a comparable number of devices exceptionally…