Related papers: Cross-Corpora Spoken Language Identification with …

The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models. Therefore, we propose an intra-source style…

This paper introduces a new method to solve the cross-domain recognition problem. Different from the traditional domain adaption methods which rely on a global domain shift for all classes between source and target domain, the proposed…

Universal domain adaptation (UniDA) transfers knowledge from a labeled source domain to an unlabeled target domain, where label spaces may differ and the target domain may contain private classes. Previous UniDA methods primarily focused on…

Domain Generalization (DG), a crucial research area, seeks to train models across multiple domains and test them on unseen ones. In this paper, we introduce a novel approach, namely, Selective Cross-Modality Distillation for Domain…

In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Despite its success, previous studies showed that PIT is plagued by…

Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes. This imbalance degrades the performance of typical…

Target-speaker voice activity detection (TS-VAD) has recently shown promising results for speaker diarization on highly overlapped speech. However, the original model requires a fixed (and known) number of speakers, which limits its…

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized…

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…

Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community. In this work, we construct a structural causal model among identity labels, identity-specific factors (clothes/shoes color…

In this work, we propose a technique to transfer speech recognition capabilities from audio speech recognition systems to visual speech recognizers, where our goal is to utilize audio data during lipreading model training. Impressive…

Extensive works have tackled Language Identification (LID) in the speech domain, however their application to the singing voice trails and performances on Singing Language Identification (SLID) can be improved leveraging recent progresses…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

With the democratization of e-commerce platforms, an increasingly diversified user base is opting to shop online. To provide a comfortable and reliable shopping experience, it's important to enable users to interact with the platform in the…

Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for…

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…

We introduce TitaNet-LID, a compact end-to-end neural network for Spoken Language Identification (LID) that is based on the ContextNet architecture. TitaNet-LID employs 1D depth-wise separable convolutions and Squeeze-and-Excitation layers…

We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental…

Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly…

Domain generalization(DG) endeavors to develop robust models that possess strong generalizability while preserving excellent discriminability. Nonetheless, pivotal DG techniques tend to improve the feature generalizability by learning…