Report: A vector quantization approach to speaker recognition

By Frank K. Soong, A. Rosenberg, B. Juang, Lawrence R. Rabiner. 1987

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Weicheng Cai
2. Jinkun Chen
3. Zexin Cai
4. Ming Li
5. Xiangjinzi Zhang
6. Xiaoqi Wang
7. Tomi H. Kinnunen
8. Haizhou Li

Citations in the corpus

• Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System (2018, methodology): “…several temporal orderless center components (or units, words, clusters, etc.), includes vector quantization (VQ) codebooks learned by K-means [12], a universal background model (UBM) learned by Gaussian Mixture Model (GMM) GMM [13, 14] or a supervised phonetically-aware acoustic model…”
• An overview of text-independent speaker recognition: From features to supervectors (2010, background): “Vector quantization (VQ) model (Burton, 1987; Hautamäki et al., 2008b; He et al., 1999; Karpov et al., 2004; Kinnunen et al., 2006b; Soong et al., 1987; Soong and Rosenberg, 1988), also known as centroid model, is one of the simplest text-independent speaker models.”
• A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification (2018, background): “It was introduced to speaker recognition in the 1980s [2].”