Related papers: On training targets for noise-robust voice activit…

Estimating noise information exactly is crucial for noise aware training in speech applications including speech enhancement (SE) which is our focus in this paper. To estimate noise-only frames, we employ voice activity detection (VAD) to…

In this work, we propose a training algorithm for an audio-visual automatic speech recognition (AV-ASR) system using deep recurrent neural network (RNN).First, we train a deep RNN acoustic model with a Connectionist Temporal Classification…

Speech Activity Detection (SAD) systems often misclassify singing as speech, leading to degraded performance in applications such as dialogue enhancement and automatic speech recognition. We introduce Singing-Robust Speech Activity…

Recent advances in Voice Activity Detection (VAD) are driven by artificial and Recurrent Neural Networks (RNNs), however, using a VAD system in battery-operated devices requires further power efficiency. This can be achieved by neuromorphic…

Under noisy environments, to achieve the robust performance of speaker recognition is still a challenging task. Motivated by the promising performance of multi-task training in a variety of image processing tasks, we explore the potential…

Target detection and recognition is a very challenging task in a wireless environment where a multitude of objects are located, whether to effectively determine their positions or to identify them and predict their moves. In this work, we…

This paper proposes a novel stable learning theory for recurrent neural networks (RNNs), so-called variational adaptive noise and dropout (VAND). As stabilizing factors for RNNs, noise and dropout on the internal state of RNNs have been…

This paper explores sentence-level multilingual Visual Speech Recognition (VSR) that can recognize different languages with a single trained model. As the massive multilingual modeling of visual data requires huge computational costs, we…

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocoders trained on real…

Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech…

Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their…

Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to…

In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses…

Vehicular communication systems face significant challenges due to high mobility and rapidly changing environments, which affect the channel over which the signals travel. To address these challenges, neural network (NN)-based channel…

Deep neural network (DNN)-based speech enhancement usually uses a clean speech as a training target. However, it is hard to collect large amounts of clean speech because the recording is very costly. In other words, the performance of…

In the field of speech enhancement, time domain methods have difficulties in achieving both high performance and efficiency. Recently, dual-path models have been adopted to represent long sequential features, but they still have limited…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

We propose noise-robust voice conversion (VC) which takes into account the recording quality and environment of noisy source speech. Conventional denoising training improves the noise robustness of a VC model by learning noisy-to-clean VC…

Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on…

Voice Type Discrimination (VTD) refers to discrimination between regions in a recording where speech was produced by speakers that are physically within proximity of the recording device ("Live Speech") from speech and other types of audio…