We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including speaker identification, verification, and clustering. We experiment with ResCNN and GRU architectures to extract the acoustic features, then mean pool to produce ...

We describe the ability of LNCC features (Locally Normalized Cepstral Coefficients) to improve speaker recognition accuracy in highly reverberant environments. We used a realistic test environment, in which we changed the number and nature of reflective surfaces in the room, creating four increasingly reverberant times from approximately 1 to 9 seconds. In this room, we re-recorded reverberated...

This paper describes a system for controlling access to web resources built using well-known speaker verification techniques. We describe the implementation of a speech verification server and an associated authentication module for the Apache web server. Speaker verification requires two inputs: a sample of the user’s speech and an identity claim for the user; typically the user’s name. Howeve...

In the past few years state-of-the-art text-dependent speaker verification technology has improved significantly in terms of the ability to accept target speakers and reject imposters. As a result, the use of speaker verification systems for real world security is increasing. Real world usage of speaker verification technology raises the issue of spoofing attacks. As part of our efforts for dev...

In this paper we present a fusion methodology for combining prompted text-dependent and text-independent speaker verification operation modalities. The fusion is performed in score level extracted from GMM-UBM single mode speaker verification engines using several machine learning algorithms for classification. In order to improve the performance we apply clustering of the score-based data befo...

This paper presents an analysis of temporal information as a feature for use in speaker verification systems. The relevance of temporal information in a speaker’s utterances is investigated, both with regard to improving the robustness of modern speaker verification systems and to detecting and deflecting recording attacks. It is shown that the use of timing information provides useful addition...