DNN Based Speaker Recognition On Short Utterances

Abstract

This paper investigates the effects of limited speech data in the context of speaker verification using deep neural network (DNN) approach. Being able to reduce the length of required speech data is important to the development of speaker verification system in real world applications. The experimental studies have found that DNN-senone-based Gaussian probabilistic linear discriminant analysis (GPLDA) system respectively achieves above 50% and 18% improvements in EER values over GMM-UBM GPLDA system on NIST 2010 coreext-coreext and truncated 15sec-15sec evaluation conditions. Further when GPLDA model is trained on short-length utterances (30sec) rather than full-length utterances (2min), DNN-senone GPLDA system achieves above 7% improvement in EER values on truncated 15sec-15sec condition. This is because short length development i-vectors have speaker, session and phonetic variation and GPLDA is able to robustly model those variations. For several real world applications, longer utter

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykanagasundaram2016dnn

Related papers

• Deep Neural Network Based I-vector Mapping For Speaker Verification Using Short Utterances (2018)0.00
• Domain Adaptation Based Speaker Recognition On Short Utterances (2016)0.00
• Deep Speaker Embeddings For Far-field Speaker Recognition On Short Utterances (2020)11.29
• End-to-end DNN Based Speaker Recognition Inspired By I-vector And PLDA (2017)10.35
• Neural Network Based Speaker Classification And Verification Systems With Enhanced Features (2017)8.60
• A Deep Neural Network For Short-segment Speaker Recognition (2019)12.74
• Deep Speaker Feature Learning For Text-independent Speaker Verification (2017)12.54
• Training Speaker Recognition Systems With Limited Data (2022)8.13