相关论文: Any-to-any Speaker Attribute Perturbation for Asyn…

Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions,…

End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which…

The rising trend of using voice as a means of interacting with smart devices has sparked worries over the protection of users' privacy and data security. These concerns have become more pressing, especially after the European Union's…

Speaker anonymization aims to suppress speaker individuality to protect privacy in speech while preserving the other aspects, such as speech content. One effective solution for anonymization is to modify the McAdams coefficient. In this…

Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual quality. Although recent advances in neural and digital signal processing-based watermarking methods have…

We introduce AnyEnhance, a unified generative model for voice enhancement that processes both speech and singing voices. Based on a masked generative model, AnyEnhance is capable of handling both speech and singing voices, supporting a wide…

Target speaker extraction focuses on isolating a specific speaker's voice from an audio mixture containing multiple speakers. To provide information about the target speaker's identity, prior works have utilized clean audio samples as…

Audio anti-spoofing for automatic speaker verification aims to safeguard users' identities from spoofing attacks. Although state-of-the-art spoofing countermeasure(CM) models perform well on specific datasets, they lack generalization when…

Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While…

Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models. However, the issue of privacy protection is an increasing concern that must be addressed. The current study…

Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a…

Speaker identification in noisy audio recordings, specifically those from collaborative learning environments, can be extremely challenging. There is a need to identify individual students talking in small groups from other students talking…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

Recent research has proposed approaches that modify speech to defend against gender inference attacks. The goal of these protection algorithms is to control the availability of information about a speaker's gender, a privacy-sensitive…

Single-channel speech enhancement is utilized in various tasks to mitigate the effect of interfering signals. Conventionally, to ensure the speech enhancement performs optimally, the speech enhancement has needed to be tuned for each task.…

Privacy-preserving voice conversion aims to remove only the attributes of speech audio that convey identity information, keeping other speech characteristics intact. This paper presents a mechanism for privacy-preserving voice conversion…

This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR…

Voice imitation aims to transform source speech to match a reference speaker's timbre and speaking style while preserving linguistic content. A straightforward approach is to train on triplets of (source, reference, target), where source…

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…