Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs

• DOI: 10.21437/interspeech.2020-1283
• Publication Date: 2020-10-27T09:22:11Z
• Authors: Seong Min Kye; Youngmoon Jung; Hae Beom Lee; Sung Ju Hwang; Hoirin Kim
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Sound (cs.SD); 4. Education; Machine Learning (stat.ML); 02 engineering and technology; Computer Science - Sound; Machine Learning (cs.LG); 03 medical and health sciences; Statistics - Machine Learning; Audio and Speech Processing (eess.AS); FOS: Electrical engineering, electronic engineering, information engineering; 0202 electrical engineering, electronic engineering, information engineering; 0305 other medical science; Electrical Engineering and Systems Science - Audio and Speech Processing

Accepted to Interspeech 2020. The codes are available at https://github.com/seongmin-kye/meta-SR<br/>In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing speaker recognition models perform poorly with such short utterances. To solve this problem, we introduce a meta-learning framework for imbalance length pairs. Specifically, we use a Prototypical Networks and train it with a support set of long utterances and a query set of short utterances of varying lengths. Further, since optimizing only for the classes in the given episode may be insufficient for learning discriminative embeddings for unseen classes, we additionally enforce the model to classify both the support and the query set against the entire set of classes in the training set. By combining these two learning schemes, our model outperforms existing state-of-the-art speaker verification models learned with a standard supervised learning framework on short utterance (1-2 seconds) on the VoxCeleb datasets. We also validate our proposed model for unseen speaker identification, on which it also achieves significant performance gains over the existing approaches. The codes are available at https://github.com/seongmin-kye/meta-SR.<br/>