English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose a Convolutional Neural Network (CNN) based speakerrecognition model for extracting robust speaker embeddings. The embedding canbe extracted efficiently with linear activation in the embedding layer. Tounderstand how the speaker recognition model operates with text-independentinput, we modify the structure to extract frame-level speaker embeddings fromeach hidden layer. We feed utterances from the TIMIT dataset to the trainednetwork and use several proxy tasks to study the networks ability to representspeech input and differentiate voice identity. We found that the networks arebetter at discriminating broad phonetic classes than individual phonemes. Inparticular, frame-level embeddings that belong to the same phonetic classes aresimilar (based on cosine distance) for the same speaker. The frame levelrepresentation also allows us to analyze the networks at the frame level, andhas the potential for other analyses to improve speaker recognition.

Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end model