Related papers: Cross-lingual Text-independent Speaker Verificatio…

Recently, researchers have utilized neural network-based speaker embedding techniques in speaker-recognition tasks to identify speakers accurately. However, speaker-discriminative embeddings do not always represent speech features such as…

ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain variance towards domain-aware/agnostic ASR, respectively. In…

We tackle the task of building supervised event trigger identification models which can generalize better across domains. Our work leverages the adversarial domain adaptation (ADA) framework to introduce domain-invariance. ADA uses…

Selecting application scenarios matching data is important for the automatic speech recognition (ASR) training, but it is difficult to measure the matching degree of the training corpus. This study proposes a unsupervised target-aware data…

Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for an unlabeled domain by transferring knowledge from a separate labeled source domain. However, most of these conventional UDA approaches make the strong assumption of…

While huge volumes of unlabeled data are generated and made available in many domains, the demand for automated understanding of visual data is higher than ever before. Most existing machine learning models typically rely on massive amounts…

Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the…

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue,…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

We present a novel speaker-independent acoustic-to-articulatory inversion (AAI) model, overcoming the limitations observed in conventional AAI models that rely on acoustic features derived from restricted datasets. To address these…

Voice technology has become ubiquitous recently. However, the accuracy, and hence experience, in different languages varies significantly, which makes the technology not equally inclusive. The availability of data for different languages is…

By using deep learning approaches, Speech Emotion Recog-nition (SER) on a single domain has achieved many excellentresults. However, cross-domain SER is still a challenging taskdue to the distribution shift between source and target…

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…

Active domain adaptation (ADA) studies have mainly addressed query selection while following existing domain adaptation strategies. However, we argue that it is critical to consider not only query selection criteria but also domain…

In this work we explore Unsupervised Domain Adaptation (UDA) of pretrained language models for downstream tasks. We introduce UDALM, a fine-tuning procedure, using a mixed classification and Masked Language Model loss, that can adapt to the…

Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain. This can be achieved by adversarial training of deep neural network (DNN) acoustic models…

Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled target images leveraging source labeled ones. In this work, we consider the Partial Domain Adaptation (PDA) variant, where we have extra source classes not present in the…

Addressing performance degradation in 3D LiDAR semantic segmentation due to domain shifts (e.g., sensor type, geographical location) is crucial for autonomous systems, yet manual annotation of target data is prohibitive. This study…

Test-time adaptation with pre-trained vision-language models has attracted increasing attention for tackling distribution shifts during the test time. Though prior studies have achieved very promising performance, they involve intensive…

One fascinating aspect of pre-trained Audio-Language Models (ALMs) learning is their impressive zero-shot generalization capability and test-time adaptation (TTA) methods aiming to improve domain performance without annotations. However,…