Related papers: End-to-End Training Approaches for Discriminative …
Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determining what input prompts would yield the target output remains…
We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of…
Foundation models (FM) have demonstrated remarkable performance across a wide range of tasks (especially in the fields of natural language processing and computer vision), primarily attributed to their ability to comprehend instructions and…
With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…
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…
In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end…
Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…
In speech machine learning, neural network models are typically designed by choosing an architecture with fixed layer sizes and structure. These models are then trained to maximize performance on metrics aligned with the task's objective.…
Independently trained machine learning models tend to learn similar features. Given an ensemble of independently trained models, this results in correlated predictions and common failure modes. Previous attempts focusing on decorrelation of…
Attention models are typically learned by optimizing one of three standard loss functions that are variously called -- soft attention, hard attention, and latent variable marginal likelihood (LVML) attention. All three paradigms are…
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…
The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to facilitate learning in a related target domain, known as…
When existing retrieval-augmented generation (RAG) solutions are intended to be used for new knowledge domains, it is necessary to update their encoders, which are taken to be pretrained large language models (LLMs). However, fully…
Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…
The success of modern deep learning is attributed to two key elements: huge amounts of training data and large model sizes. Where a vast amount of data allows the model to learn more features, the large model architecture boosts the…
Combining different data modalities enables deep neural networks to tackle complex tasks more effectively, making multimodal learning increasingly popular. To harness multimodal data closer to end users, it is essential to integrate…
We investigate neural techniques for end-to-end computational argumentation mining (AM). We frame AM both as a token-based dependency parsing and as a token-based sequence tagging problem, including a multi-task learning setup. Contrary to…
Diffusion Probabilistic Models (DPMs) suffer from inefficient inference due to their slow sampling and high memory consumption, which limits their applicability to various medical imaging applications. In this work, we propose a novel…
As one of the fundamental tasks in computer vision, semantic segmentation plays an important role in real world applications. Although numerous deep learning models have made notable progress on several mainstream datasets with the rapid…
In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers. Both lattice-free and…