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

Fundamental frequency is one of the most important parameters of humanspeech, of importance for the classification of accent, gender, speakingstyles, speaker identification, age, among others. The proper detection of thisparameter remains as an important challenge for severely degraded signals. Inprevious references for detecting fundamental frequency in noisy speech usingdeep learning, the networks, such as Long Short-term Memory (LSTM) has beeninitialized with random weights, and then trained following a back-propagationthrough time algorithm. In this work, a proposal for a more efficientinitialization, based on a supervised training using an Auto-associativenetwork, is presented. This initialization is a better starting point for thedetection of fundamental frequency in noisy speech. The advantages of thisinitialization are noticeable using objective measures for the accuracy of thedetection and for the training of the networks, under the presence of additivewhite noise at different signal-to-noise levels.

Supervised Initialization of LSTM Networks for Fundamental Frequency Detection in Noisy Speech Signals