Related papers: Dynamic Recognition of Speakers for Consent Manage…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial…

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…

This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output…

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Dysarthric speech reconstruction is challenging due to its pathological sound patterns. Preserving speaker identity, especially without access to normal speech, is a key challenge. Our proposed approach uses contrastive learning to extract…

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…

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…

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…

Unsupervised representation learning has shown remarkable achievement by reducing the performance gap with supervised feature learning, especially in the image domain. In this study, to extend the technique of unsupervised learning to the…

Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker…

Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overcome the first…

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…

Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second performs the…

In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain…

This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to…