Related papers: Optimization of DNN-based speaker verification mod…

As soon as abstract mathematical computations were adapted to computation on digital computers, the problem of efficient representation, manipulation, and communication of the numerical values in those computations arose. Strongly related…

Deep learning methods have established a significant place in image classification. While prior research has focused on enhancing final outcomes, the opaque nature of the decision-making process in these models remains a concern for…

A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown…

This research aims to optimize intricate learning models by implementing quantization and bit-depth optimization techniques. The objective is to significantly cut time complexity while preserving model efficiency, thus addressing the…

The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN with the…

Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…

End-to-End Neural Diarization (EEND) systems produce frame-level probabilistic speaker activity estimates, yet since evaluation focuses primarily on Diarization Error Rate (DER), the reliability and calibration of these confidence scores…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Reducing the memory footprint of Machine Learning (ML) models, especially Deep Neural Networks (DNNs), is imperative to facilitate their deployment on resource-constrained edge devices. However, a notable drawback of DNN models lies in…

Transformer-based models have made remarkable advancements in various NLP areas. Nevertheless, these models often exhibit vulnerabilities when confronted with adversarial attacks. In this paper, we explore the effect of quantization on the…

We propose a deep beamforming framework for enhancing target speaker(s) in multi-speaker environments. A deep neural network (DNN) is trained to estimate beamforming weights directly from noisy multichannel inputs while satisfying linear…

Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs.…

Deep Neural Networks (DNNs) have gained considerable attention in the past decades due to their astounding performance in different applications, such as natural language modeling, self-driving assistance, and source code understanding.…

Knowledge distillation (KD) is a very popular method for model size reduction. Recently, the technique is exploited for quantized deep neural networks (QDNNs) training as a way to restore the performance sacrificed by word-length reduction.…

We investigate pruning and quantization for deep neural networks. Our goal is to achieve extremely high sparsity for quantized networks to enable implementation on low cost and low power accelerator hardware. In a practical scenario, there…

End-to-end performance estimation and measurement of deep neural network (DNN) systems become more important with increasing complexity of DNN systems consisting of hardware and software components. The methodology proposed in this paper…

Quantization of weights and activations in Deep Neural Networks (DNNs) is a powerful technique for network compression, and has enjoyed significant attention and success. However, much of the inference-time benefit of quantization is…

Enhancing noisy speech is an important task to restore its quality and to improve its intelligibility. In traditional non-machine-learning (ML) based approaches the parameters required for noise reduction are estimated blindly from the…

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

Deep Neural Networks (DNNs) have gained immense success in cognitive applications and greatly pushed today's artificial intelligence forward. The biggest challenge in executing DNNs is their extremely data-extensive computations. The…