相关论文: ESE: Efficient Speech Recognition Engine with Spar…

Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficiency in decoding. In conventional LSTM-CTC based models, a…

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…

The next significant step in the evolution and proliferation of artificial intelligence technology will be the integration of neural network (NN) models within embedded and mobile systems. This calls for the design of compact, energy…

Efficient adaption of large language models (LLMs) on edge devices is essential for applications requiring continuous and privacy-preserving adaptation and inference. However, existing tuning techniques fall short because of the high…

Deploying large language models (LLMs) on edge platforms is challenged by their high computational and memory demands. Although recent low-bit quantization methods (e.g., BitNet, DeepSeek) compress weights to as little as 1.58 bits with…

In this letter, we propose an energy-efficient split learning (SL) framework for fine-tuning large language models (LLMs) using geo-distributed personal data at the network edge, where LLMs are split and alternately across massive mobile…

Neural networks have demonstrated their outstanding performance in a wide range of tasks. Specifically recurrent architectures based on long-short term memory (LSTM) cells have manifested excellent capability to model time dependencies in…

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

Real-time target speaker extraction (TSE) is intended to extract the desired speaker's voice from the observed mixture of multiple speakers in a streaming manner. Implementing real-time TSE is challenging as the computational complexity…

Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger. Since a different copy of the model is required for each task, this…

Self-Supervised Learning (SSL) models have demonstrated exceptional performance in various speech tasks, particularly in low-resource and multilingual domains. Recent works show that fusing diverse SSL models could achieve superior…

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware…

EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since published in ISCA'16, it opened a new design space to…

Power system state estimation (PSSE) is commonly formulated as weighted least-square (WLS) algorithm and solved using iterative methods such as Gauss-Newton methods. However, iterative methods have become more sensitive to system operating…

This study investigates the application of advanced machine learning models, specifically Long Short-Term Memory (LSTM) networks and Gradient Booster models, for accurate energy consumption estimation within a Kubernetes cluster…

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to…

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Sparse Matrix-Vector Multiplication (SpMV) has become a critical performance bottleneck in the local deployment of sparse Large Language Models (LLMs), where inference predominantly operates on workloads during the decoder phase with a…

We propose a workflow for speech emotion recognition (SER) that combines pre-trained representations with automated hyperparameter optimisation (HPO). Using SpeechBrain wav2vec2-base model fine-tuned on IEMOCAP as the encoder, we compare…