2019/08/27 by Xueyi Wang, Wang, Xueyi, Lantian Li +3 · 1 citation
Computer Science · Engineering · Mathematics · #Adaptation (eye) #Artificial intelligence #Artificial neural network #Audio and Speech Processing (eess.AS) #Autoencoder #Computer science #Domain (mathematical analysis) #Domain adaptation #Embedding #Encoder #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Mathematics #Music and Audio Processing #Pattern recognition (psychology) #Set (abstract data type) #Sound (cs.SD) #Space (punctuation) #Speaker recognition #Speaker verification #Speech Recognition and Synthesis #Speech and Audio Processing #Speech recognition #Training set #cs.LG #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1908.10092
published in arXiv (Cornell University) (Cornell University)
arxiv created 2019/08/27 · openalex publication_date 2019/08/27 · arxiv updated 2019/08/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Deep speaker embedding has achieved satisfactory performance in speaker verification. By enforcing the neural model to discriminate the speakers in the training set, deep speaker embedding (called `x-vectors`) can be derived from the hidden layers. Despite its good performance, the present embedding model is highly domain sensitive, which means that it often works well in domains whose acoustic condition matches that of the training data (in-domain), but degrades in mismatched domains (out-of-domain). In this paper, we present a domain adaptation approach based on Variational Auto-Encoder (VAE). This model transforms x-vectors to a regularized latent space; within this latent space, a small amount of data from the target domain is sufficient to accomplish the adaptation. Our experiments demonstrated that by this VAE-adaptation approach, speaker embeddings can be easily transformed to the target domain, leading to noticeable performance improvement.