Search Results for author:
Found 9 papers, 1 papers with code
Attention-Guided Adaptation for Code-Switching Speech Recognition
The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition.
Contrastive Speaker Embedding With Sequential Disentanglement
Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only.
Asymmetric Clean Segments-Guided Self-Supervised Learning for Robust Speaker Verification
Contrastive self-supervised learning (CSL) for speaker verification (SV) has drawn increasing interest recently due to its ability to exploit unlabeled data.
Parameter-Efficient Learning for Text-to-Speech Accent Adaptation
This paper presents a parameter-efficient learning (PEL) to develop a low-resource accent adaptation for text-to-speech (TTS).
Disentangled Mask Attention in Transformer
To strengthen the sequential learning representation, this paper presents a new disentangled mask attention in transformer where the redundant features are reduced and the semantic information is enriched.
Variational Disentangled Attention for Regularized Visual Dialog
One of the most important challenges in a visual dialog is to effectively extract the information from a given image and its historical conversation which are related to the current question.
Deep Bayesian Natural Language Processing
The {``}distribution function{''} in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated.
BALSON: Bayesian Least Squares Optimization with Nonnegative L1-Norm Constraint
In order to explicitly characterize the nonnegative L1-norm constraint of the parameters, we further approximate the true posterior distribution by a Dirichlet distribution.
