Compact Speaker Embedding: lrx-vector
Deep neural networks (DNN) have recently been widely used in speaker recognition systems, achieving state-of-the-art performance on various benchmarks. The x-vector architecture is especially popular in this research community, due to its excellent performance and manageable computational complexity. In this paper, we present the lrx-vector system, which is the low-rank factorized version of the x-vector embedding network. The primary objective of this topology is to further reduce the memory requirement of the speaker recognition system. We discuss the deployment of knowledge distillation for training the lrx-vector system and compare against low-rank factorization with SVD. On the VOiCES 2019 far-field corpus we were able to reduce the weights by 28% compared to the full-rank x-vector system while keeping the recognition rate constant (1.83% EER).
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge DistillationSpeaker RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adapting End-to-End Neural Speaker Verification to New Languages and Recording Conditions with Adversarial Training
In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a…
Speaker VerificationText-Independent Speaker VerificationDistilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification
Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in r…
Knowledge DistillationSpeaker VerificationDr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition
Many neural network speaker recognition systems model each speaker using a fixed-dimensional embedding vector. These embeddings are generally compared using either linear or 2nd-order scoring and, until recently, do not …
Speaker RecognitionMargin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained…
Speaker RecognitionDNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be app…
Speech Synthesis