Related papers: Dynamic Encoder Size Based on Data-Driven Layer-wi…

In this paper, we propose a dynamic cascaded encoder Automatic Speech Recognition (ASR) model, which unifies models for different deployment scenarios. Moreover, the model can significantly reduce model size and power consumption without…

The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data. However, this trend has made model training prohibitively costly and imposed computational demands. While data…

In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints. However, multiple models with different…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy…

Deploying an end-to-end automatic speech recognition (ASR) model on mobile/embedded devices is a challenging task, since the device computational power and energy consumption requirements are dynamically changed in practice. To overcome the…

Neural network pruning offers an effective method for compressing a multilingual automatic speech recognition (ASR) model with minimal performance loss. However, it entails several rounds of pruning and re-training needed to be run for each…

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

ASR systems are deployed across diverse environments, each with specific hardware constraints. We use supernet training to jointly train multiple encoders of varying sizes, enabling dynamic model size adjustment to fit hardware constraints…

The state of the art of many learning tasks, e.g., image classification, is advanced by collecting larger datasets and then training larger models on them. As the outcome, the increasing computational cost is becoming unaffordable. In this…

Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems. However, due to their high computational and memory demands, deploying RNNs on resource constrained mobile devices is a challenging task. To…

Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint…

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET…

On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can benefit from training them jointly to take advantage of the…

We propose a novel parameter-efficient training (PET) method for large language models that adapts models to downstream tasks by optimizing a small subset of the existing model parameters. Unlike prior methods, this subset is not fixed in…

Deep learning recommendation systems at scale have provided remarkable gains through increasing model capacity (i.e. wider and deeper neural networks), but it comes at significant training cost and infrastructure cost. Model pruning is an…

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…

Automatic Speech Recognition (ASR) models need to be optimized for specific hardware before they can be deployed on devices. This can be done by tuning the model's hyperparameters or exploring variations in its architecture. Re-training and…

From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets. To navigate the Pareto front of model accuracy vs model size, researchers are…

We present a novel network pruning algorithm called Dynamic Sparse Training that can jointly find the optimal network parameters and sparse network structure in a unified optimization process with trainable pruning thresholds. These…