相关论文: Pushing the limits of self-supervised speaker veri…

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training strategy to enable the…

Deep audio representation learning using multi-modal audio-visual data often leads to a better performance compared to uni-modal approaches. However, in real-world scenarios both modalities are not always available at the time of inference,…

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we…

Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…

Deploying speaker verification on resource-constrained devices remains challenging due to the computational cost of high-capacity models; knowledge distillation (KD) offers a remedy. Classical KD entangles target confidence with non-target…

Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo…

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…

Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these…

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Driven by encouraging results on a wide range of tasks, the field of NLP is experiencing an accelerated race to develop bigger language models. This race for bigger models has also underscored the need to continue the pursuit of practical…

Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial…

Consistency regularization has been widely studied in recent semisupervised semantic segmentation methods, and promising performance has been achieved. In this work, we propose a new consistency regularization framework, termed mutual…

End-to-end neural diarization models have usually relied on a multilabel-classification formulation of the speaker diarization problem. Recently, we proposed a powerset multiclass formulation that has beaten the state-of-the-art on multiple…

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learning methods have achieved high-quality results, their…

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…

Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a significant challenge, particularly when systems conditioned on speaker embeddings fail to generalize to unseen speakers. In this work, we propose…

We present improvements to speaker diarization in the two-stage end-to-end neural diarization with vector clustering (EEND-VC) framework. The first stage employs a Conformer-based EEND model with WavLM features to infer frame-level speaker…