Related papers: The CORAL+ Algorithm for Unsupervised Domain Adapt…
The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…
Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…
The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…
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…
Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framework based on…
Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers. The parameters of PLDA are often estimated by maximizing the objective…
Spoken language recognition (SLR) refers to the automatic process used to determine the language present in a speech sample. SLR is an important task in its own right, for example, as a tool to analyze or categorize large amounts of…
Probabilistic linear discriminant analysis (PLDA) is a popular normalization approach for the i-vector model, and has delivered state-of-the-art performance in speaker recognition. A potential problem of the PLDA model, however, is that it…
Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems. The common wisdom is to collect cross-domain data and train a multi-domain PLDA model, with the hope to learn a…
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…
Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts adopt the Class…
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…
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…
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…
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,…
This paper explores how the in- and out-domain probabilistic linear discriminant analysis (PLDA) speaker verification behave when enrolment and verification lengths are reduced. Experiment studies have found that when full-length utterance…
High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually…
State-of-art speaker verification (SV) systems use a back-end model to score the similarity of speaker embeddings extracted from a neural network model. The commonly used back-end models are the cosine scoring and the probabilistic linear…
Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks…
Dysarthric speech detection (DSD) systems aim to detect characteristics of the neuromotor disorder from speech. Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target…