Related papers: HiddenSpeaker: Generate Imperceptible Unlearnable …

The goal of this contribution is to use a parametric speech synthesis system for reducing background noise and other interferences from recorded speech signals. In a first step, Hidden Markov Models of the synthesis system are trained. Two…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized…

Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech. However, malicious uses of such tools are possible and likely, posing a serious threat to our…

One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training.…

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including…

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…

In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…

Synthesizing the voices of unseen speakers remains a persisting challenge in multi-speaker text-to-speech (TTS). Existing methods model speaker characteristics through speaker conditioning during training, leading to increased model…

Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues,…

Despite the recent success of deep learning for many speech processing tasks, single-microphone, speaker-independent speech separation remains challenging for two main reasons. The first reason is the arbitrary order of the target and…

We propose DarkStream, a streaming speech synthesis model for real-time speaker anonymization. To improve content encoding under strict latency constraints, DarkStream combines a causal waveform encoder, a short lookahead buffer, and…

Recent advancements in speaker verification techniques show promise, but their performance often deteriorates significantly in challenging acoustic environments. Although speech enhancement methods can improve perceived audio quality, they…

Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…

Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would…

Recently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, the application of diffusion models for synthesizing time-varying audio faces…

In our previous work, we proposed a language-independent speaker anonymization system based on self-supervised learning models. Although the system can anonymize speech data of any language, the anonymization was imperfect, and the speech…