Related papers: Effective and Efficient One-pass Compression of Sp…

There are growing interests in adapting large-scale language models using parameter-efficient fine-tuning methods. However, accelerating the model itself and achieving better inference efficiency through model compression has not been…

We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using…

Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from…

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due…

This paper presents a speech enhancement method, where an adaptive threshold is statistically determined based on Gaussian modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of noisy speech. In order to…

Recent studies have shown that post-deployment adaptation can improve the robustness of speech enhancement models in unseen noise conditions. However, existing methods often incur prohibitive computational and memory costs, limiting their…

Introducing sparsity in a neural network has been an efficient way to reduce its complexity while keeping its performance almost intact. Most of the time, sparsity is introduced using a three-stage pipeline: 1) train the model to…

Communication overhead severely hinders the scalability of distributed machine learning systems. Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training.…

We propose a framework for compressing state-of-the-art Single Shot MultiBox Detector (SSD). The framework addresses compression in the following stages: Sparsity Induction, Filter Selection, and Filter Pruning. In the Sparsity Induction…

The components underpinning PLMs -- large weight matrices -- were shown to bear considerable redundancy. Matrix factorization, a well-established technique from matrix theory, has been utilized to reduce the number of parameters in PLM.…

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection.…

Leveraging second-order information about the loss at the scale of deep networks is one of the main lines of approach for improving the performance of current optimizers for deep learning. Yet, existing approaches for accurate full-matrix…

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…

Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…

Deep learning models have introduced various intelligent applications to edge devices, such as image classification, speech recognition, and augmented reality. There is an increasing need of training such models on the devices in order to…

Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production…

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition. We propose data selection techniques to…

This work presents a speech-to-text system "Pisets" for scientists and journalists which is based on a three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with…