Related papers: Efficient Ensemble for Multimodal Punctuation Rest…

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…

In this research, we propose a new low-precision framework, TENT, to leverage the benefits of a tapered fixed-point numerical format in TinyML models. We introduce a tapered fixed-point quantization algorithm that matches the numerical…

The exponential growth of multivariate time series data from sensor networks in domains like industrial monitoring and smart cities requires efficient and accurate forecasting models. Current deep learning methods often fail to adequately…

Recurrent neural networks are widely used in speech and language processing. Due to dependency on the past, standard algorithms for training these models, such as back-propagation through time (BPTT), cannot be efficiently parallelised.…

Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These errors usually take the form of homonyms. We show how…

Accurate recognition of sign language in healthcare communication poses a significant challenge, requiring frameworks that can accurately interpret complex multimodal gestures. To deal with this, we propose FusionEnsemble-Net, a novel…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Punctuation is critical in understanding natural language text. Currently, most automatic speech recognition (ASR) systems do not generate punctuation, which affects the performance of downstream tasks, such as intent detection and slot…

Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks. However, their excessive amount of parameters hinders them from efficient deployment on edge devices. Binarization of the BERT models can…

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…

Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is…

Precise pointer analysis is a foundational component of many client analyses and optimizations. Scaling flow- and context-sensitive pointer analysis has been a long-standing challenge, suffering from combinatorial growth in both memory…

Models based on attention mechanisms have shown unprecedented speech recognition performance. However, they are computationally expensive and unnecessarily complex for keyword spotting, a task targeted to small-footprint devices. This work…

For a speech-enhancement algorithm, it is highly desirable to simultaneously improve perceptual quality and recognition rate. Thanks to computational costs and model complexities, it is challenging to train a model that effectively…

Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, e.g. semantic segmentation, creating an ensemble of learners that needs to be…

Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble…

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving estimation accuracy with little consideration on efficiency. Several…

Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize…

To accomplish punctuation restoration, most existing methods focus on introducing extra information (e.g., part-of-speech) or addressing the class imbalance problem. Recently, large-scale transformer-based pre-trained language models (PLMS)…