Speaker recognition is a task of identifying persons from their voices. Recently, deep
learning has dramatically revolutionized speaker recognition. However, there is lack of …

The construction of speaker-specific acoustic models for automatic speaker recognition is
almost exclusively based on deep neural network-based speaker embeddings. This work …

Different people speak with diverse personalized speaking styles. Although existing one-
shot talking head methods have made significant progress in lip sync, natural facial …

In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker
representations. We employ 1D depth-wise separable convolutions with Squeeze-and …

We propose the (): S emantically-A ligned M ultimodal U tterance-level Cross-L ingual S
peech R epresentation learning framework. Unlike previous works on speech representation …

Diffusion models have shown remarkable success in a variety of downstream generative
tasks, yet remain under-explored in the important and challenging expressive talking head …

Any-to-any voice conversion (VC) aims to convert the timbre of utterances from and to any
speakers seen or unseen during training. Various any-to-any VC approaches have been …

Speech quality assessment has been a critical issue in speech processing for decades.
Existing automatic evaluations usually require clean references or parallel ground truth data …

For self-supervised speaker verification, the quality of pseudo labels decides the upper
bound of the system due to the massive unreliable labels. In this work, we propose dynamic …

Initially developed for natural language processing (NLP), Transformer model is now widely
used for speech processing tasks such as speaker recognition, due to its powerful sequence …