相关论文: Masking Kernel for Learning Energy-Efficient Repre…

Attending to the speech stream of interest in multi-talker environments can be a challenging task, particularly for listeners with hearing impairment. Research suggests that neural responses assessed with electroencephalography (EEG) are…

This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…

Recent breakthrough technological progressions of powerful mobile computing resources such as low-cost mobile GPUs along with cutting-edge, open-source software architectures have enabled high-performance deep learning on mobile platforms.…

In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings. The embedding can be extracted efficiently with linear activation in the embedding layer. To understand…

Wireless distributed systems as used in sensor networks, Internet-of-Things and cyber-physical systems, impose high requirements on resource efficiency. Advanced preprocessing and classification of data at the network edge can help to…

Estimating time-frequency domain masks for single-channel speech enhancement using deep learning methods has recently become a popular research field with promising results. In this paper, we propose a novel components loss (CL) for the…

Spiking neural networks (SNNs) have been gaining interest as energy-efficient alternatives of conventional artificial neural networks (ANNs) due to their event-driven computation. Considering the future deployment of SNN models to…

A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…

This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…

Many studies estimate energy consumption using proxy metrics like memory usage, FLOPs, and inference latency, with the assumption that reducing these metrics will also lower energy consumption in neural networks. This paper, however, takes…

Speech restoration aims at restoring high quality speech in the presence of a diverse set of distortions. Although several deep learning paradigms have been studied for this task, the power of the recently emerging language models has not…

In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…

For speech recognition, deep neural networks (DNNs) have significantly improved the recognition accuracy in most of benchmark datasets and application domains. However, compared to the conventional Gaussian mixture models, DNN-based…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Time-frequency (T-F) domain masking is a mainstream approach for single-channel speech enhancement. Recently, focuses have been put to phase prediction in addition to amplitude prediction. In this paper, we propose a…

After their introduction to robust speech recognition, power normalized cepstral coefficient (PNCC) features were successfully adopted to other tasks, including speaker verification. However, as a feature extractor with long-term operations…

Speech Enhancement (SE) in audio devices is often supported by auxiliary modules for Voice Activity Detection (VAD), SNR estimation, or Acoustic Scene Classification to ensure robust context-aware behavior and seamless user experience. Just…

The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we…

Recently, progressive learning has shown its capacity to improve speech quality and speech intelligibility when it is combined with deep neural network (DNN) and long short-term memory (LSTM) based monaural speech enhancement algorithms,…

Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved…