Strategies for end-to-end text-independent speaker verification

Weiwei Lin, Man Wai Mak, Jen Tzung Chien

Research output: Journal article publicationConference articleAcademic researchpeer-review

1 Citation (Scopus)


State-of-the-art speaker verification (SV) systems typically consist of two distinct components: a deep neural network (DNN) for creating speaker embeddings and a backend for improving the embeddings' discriminative ability. The question which arises is: Can we train an SV system without a backend? We believe that the backend is to compensate for the fact that the network is trained entirely on short speech segments. This paper shows that with several modifications to the x-vector system, DNN embeddings can be directly used for verification. The proposed modifications include: (1) a mask-pooling layer that augments the training samples by randomly masking the frame-level activations and then computing temporal statistics, (2) a sampling scheme that produces diverse training samples by randomly splicing several speech segments from each utterance, and (3) additional convolutional layers designed to reduce the temporal resolution to save computational cost. Experiments on NIST SRE 2016 and 2018 show that our method can achieve state-of-the-art performance with simple cosine similarity and requires only half of the computational cost of the x-vector network.

Original languageEnglish
Pages (from-to)4308-4312
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2020
Event21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China
Duration: 25 Oct 202029 Oct 2020


  • Deep neural network
  • End-to-end speaker embedding
  • Speaker verification
  • X-vector

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this