English
Related papers

Related papers: USM RNN-T model weights binarization

200 papers

Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed…

Machine Learning · Computer Science 2024-07-04 Yipin Guo , Yilin Lang , Qinyuan Ren

We present a psychoacoustically enhanced cost function to balance network complexity and perceptual performance of deep neural networks for speech denoising. While training the network, we utilize perceptual weights added to the ordinary…

Sound · Computer Science 2018-01-31 Kai Zhen , Aswin Sivaraman , Jongmo Sung , Minje Kim

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

Computation and Language · Computer Science 2024-01-09 Yiming Wang , Jinyu Li

We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we improve the conditioning…

Machine Learning · Computer Science 2016-06-07 Tim Salimans , Diederik P. Kingma

This paper investigates the scaling properties of Recurrent Neural Network Language Models (RNNLMs). We discuss how to train very large RNNs on GPUs and address the questions of how RNNLMs scale with respect to model size, training-set…

Computation and Language · Computer Science 2015-02-03 Will Williams , Niranjani Prasad , David Mrva , Tom Ash , Tony Robinson

Computational complexity is critical when deploying deep learning-based speech denoising models for on-device applications. Most prior research focused on optimizing model architectures to meet specific computational cost constraints, often…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-15 Hangting Chen , Jianwei Yu , Chao Weng

Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To…

Computation and Language · Computer Science 2020-04-10 Shaojie Jiang , Thomas Wolf , Christof Monz , Maarten de Rijke

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Computation and Language · Computer Science 2022-08-30 Boyang Xue , Shoukang Hu , Junhao Xu , Mengzhe Geng , Xunying Liu , Helen Meng

Transformer models have revolutionized natural language processing with their unparalleled ability to grasp complex contextual relationships. However, the vast number of parameters in these models has raised concerns regarding computational…

Machine Learning · Computer Science 2023-10-10 Sia Gholami , Marwan Omar

Although quantum machine learning has shown great promise, the practical application of quantum computers remains constrained in the noisy intermediate-scale quantum era. To take advantage of quantum machine learning, we investigate the…

Quantum Physics · Physics 2026-02-20 Shaozhi Li , M Sabbir Salek , Mashrur Chowdhury , Yao Wang

With the growing incorporation of deep neural network (DNN) models into modern software systems, the prohibitive construction costs have become a significant challenge. Model reuse has been widely applied to reduce training costs, but…

Machine Learning · Computer Science 2025-08-18 Xiaohan Bi , Binhang Qi , Hailong Sun , Xiang Gao , Yue Yu , Xiaojun Liang

In recent years, the compression of large language models (LLMs) has emerged as a key problem in facilitating LLM deployment on resource-limited devices, reducing compute costs, and mitigating the environmental footprint due to large-scale…

Machine Learning · Computer Science 2025-05-07 Sean I. Young

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Computation and Language · Computer Science 2017-05-30 Shane Walker , Morten Pedersen , Iroro Orife , Jason Flaks

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Computation and Language · Computer Science 2025-02-06 Rhea Sanjay Sukthanker , Benedikt Staffler , Frank Hutter , Aaron Klein

The FloatSD technology has been shown to have excellent performance on low-complexity convolutional neural networks (CNNs) training and inference. In this paper, we applied FloatSD to recurrent neural networks (RNNs), specifically long…

Machine Learning · Computer Science 2020-01-24 Yu-Tung Liu , Tzi-Dar Chiueh

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

Neural and Evolutionary Computing · Computer Science 2017-02-28 Joachim Ott , Zhouhan Lin , Ying Zhang , Shih-Chii Liu , Yoshua Bengio

Learning long term dependencies in recurrent networks is difficult due to vanishing and exploding gradients. To overcome this difficulty, researchers have developed sophisticated optimization techniques and network architectures. In this…

Neural and Evolutionary Computing · Computer Science 2015-04-09 Quoc V. Le , Navdeep Jaitly , Geoffrey E. Hinton

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary…

Computation and Language · Computer Science 2024-02-28 Shuming Ma , Hongyu Wang , Lingxiao Ma , Lei Wang , Wenhui Wang , Shaohan Huang , Li Dong , Ruiping Wang , Jilong Xue , Furu Wei

The weight matrix (WM) of a neural network (NN) is its program. The programs of many traditional NNs are learned through gradient descent in some error function, then remain fixed. The WM of a self-referential NN, however, can keep rapidly…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Imanol Schlag , Róbert Csordás , Jürgen Schmidhuber

In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such…

Machine Learning · Computer Science 2018-10-03 Zhezhi He , Deliang Fan