Related papers: Noise-robust voice conversion with domain adversar…

This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.…

This paper introduces a novel audio-to-image encoding framework that integrates multiple dimensions of voice characteristics into a single RGB image for speaker recognition. In this method, the green channel encodes raw audio data, the red…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…

The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…

All previous methods for audio-driven talking head generation assume the input audio to be clean with a neutral tone. As we show empirically, one can easily break these systems by simply adding certain background noise to the utterance or…

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…

Voice conversion is to generate a new speech with the source content and a target voice style. In this paper, we focus on one general setting, i.e., non-parallel many-to-many voice conversion, which is close to the real-world scenario. As…

In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) system to convert source speech with arbitrary language…

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…

Although the semantic communications have exhibited satisfactory performance in a large number of tasks, the impact of semantic noise and the robustness of the systems have not been well investigated. Semantic noise is a particular kind of…

Numerous voice conversion (VC) techniques have been proposed for the conversion of voices among different speakers. Although good quality of the converted speech can be observed when VC is applied in a clean environment, the quality…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach to the problem. This allows us to automatically model various aspects of this…

Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important…

Speaker recognition systems (SRSs) have recently been shown to be vulnerable to adversarial attacks, raising significant security concerns. In this work, we systematically investigate transformation and adversarial training based defenses…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

Building cross-lingual voice conversion (VC) systems for multiple speakers and multiple languages has been a challenging task for a long time. This paper describes a parallel non-autoregressive network to achieve bilingual and code-switched…

In this paper, we propose a noise robust bottleneck feature representation which is generated by an adversarial network (AN). The AN includes two cascade connected networks, an encoding network (EN) and a discriminative network (DN).…