Related papers: A Fully Convolutional Neural Network Approach to E…

We propose an algorithm to extract noise-robust acoustic features from noisy speech. We use Total Variability Modeling in combination with Non-negative Matrix Factorization (NMF) to learn a total variability subspace and adapt NMF…

Speaker recognition systems based on Convolutional Neural Networks (CNNs) are often built with off-the-shelf backbones such as VGG-Net or ResNet. However, these backbones were originally proposed for image classification, and therefore may…

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…

This paper describes our submission to the Second Clarity Enhancement Challenge (CEC2), which consists of target speech enhancement for hearing-aid (HA) devices in noisy-reverberant environments with multiple interferers such as music and…

In this paper, we propose a model to perform style transfer of speech to singing voice. Contrary to the previous signal processing-based methods, which require high-quality singing templates or phoneme synchronization, we explore a…

Multi-channel speech enhancement aims to extract clean speech from a noisy mixture using signals captured from multiple microphones. Recently proposed methods tackle this problem by incorporating deep neural network models with spatial…

We propose an end-to-end speaker verification system based on the neural network and trained by a loss function with less computational complexity. The end-to-end speaker verification system in this paper consists of a ResNet architecture…

In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neural network (CT-DNN) model. By enforcing the model to…

The ability of deep neural networks (DNNs) to represent phonotactic generalizations derived from lexical learning remains an open question. This study (1) investigates the lexically-invariant generalization capacity of generative…

This paper describes the practical response- and performance-aware development of online speech enhancement for an augmented reality (AR) headset that helps a user understand conversations made in real noisy echoic environments (e.g.,…

Recently deep neural networks (DNNs) have been used to learn speaker features. However, the quality of the learned features is not sufficiently good, so a complex back-end model, either neural or probabilistic, has to be used to address the…

Recently several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short…

Most phoneme recognition state-of-the-art systems rely on a classical neural network classifiers, fed with highly tuned features, such as MFCC or PLP features. Recent advances in ``deep learning'' approaches questioned such systems, but…

Noise and inconsistency commonly exist in real-world information networks, due to inherent error-prone nature of human or user privacy concerns. To date, tremendous efforts have been made to advance feature learning from networks, including…

Humans can listen to a target speaker even in challenging acoustic conditions that have noise, reverberation, and interfering speakers. This phenomenon is known as the cocktail-party effect. For decades, researchers have focused on…

We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only…

Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to…

Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware…

The field of speech separation, addressing the "cocktail party problem", has seen revolutionary advances with DNNs. Speech separation enhances clarity in complex acoustic environments and serves as crucial pre-processing for speech…

This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studies of deep neural…