Related papers: Unsupervised Adaptation of SPLDA
Multi-source domain adaptation (MSDA) addresses the challenge of learning a label prediction function for an unlabeled target domain by leveraging both the labeled data from multiple source domains and the unlabeled data from the target…
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data. Being able to improve cross-lingual speaker verification system using unlabeled data can greatly increase the…
Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can exhibit large…
We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new…
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…
IR models using a pretrained language model significantly outperform lexical approaches like BM25. In particular, SPLADE, which encodes texts to sparse vectors, is an effective model for practical use because it shows robustness to…
PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labelled development data, which is highly…
Given an existing system learned from previous source domains, it is desirable to adapt the system to new domains without accessing and forgetting all the previous domains in some applications. This problem is known as domain expansion.…
In diarization, the PLDA is typically used to model an inference structure which assumes the variation in speech segments be induced by various speakers. The speaker variation is then learned from the training data. However, human…
Speech recognition systems are often highly domain dependent, a fact widely reported in the literature. However the concept of domain is complex and not bound to clear criteria. Hence it is often not evident if data should be considered to…
Probabilistic linear discriminant analysis (PLDA) is a method used for biometric problems like speaker or face recognition that models the variability of the samples using two latent variables, one that depends on the class of the sample…
Recent studies have shown that pseudo labels can contribute to unsupervised domain adaptation (UDA) for speaker verification. Inspired by the self-training strategies that use an existing classifier to label the unlabeled data for…
It is a strong prerequisite to access source data freely in many existing unsupervised domain adaptation approaches. However, source data is agnostic in many practical scenarios due to the constraints of expensive data transmission and data…
Recent work has shown that it is possible to train an $\textit{unsupervised}$ automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised ASR methods assume that no labeled data can be used for…
We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a…
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…
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions.…
In some speaker recognition scenarios we find conversations recorded simultaneously over multiple channels. That is the case of the interviews in the NIST SRE dataset. To take advantage of that, we propose a modification of the PLDA model…
Probabilistic Linear Discriminant Analysis (PLDA) is a popular tool in open-set classification/verification tasks. However, the Gaussian assumption underlying PLDA prevents it from being applied to situations where the data is clearly…
Probabilistic Linear Discriminant Analysis (PLDA) has become state-of-the-art method for modeling $i$-vector space in speaker recognition task. However the performance degradation is observed if enrollment data size differs from one speaker…