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 study, we present an innovative technique for speaker adaptation inorder to improve the accuracy of segmentation with application tounit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques forspeaker adaptation, which attempt to improve the accuracy of the segmentationusing acoustic models that are more robust in the face of the speaker'scharacteristics, we aim to use only context dependent characteristicsextrapolated with linguistic analysis techniques. In simple terms, we use theintuitive idea that context dependent information is tightly correlated withthe related acoustic waveform. We propose a statistical model, which predictscorrecting values to reduce the systematic error produced by a state-of-the-artHidden Markov Model (HMM) based speech segmentation. Our approach consists oftwo phases: (1) identifying context-dependent phonetic unit classes (forinstance, the class which identifies vowels as being the nucleus ofmonosyllabic words); and (2) building a regression model that associates themean error value made by the ASR during the segmentation of a single speakercorpus to each class. The success of the approach is evaluated by comparing thecorrected boundaries of units and the state-of-the-art HHM segmentation againsta reference alignment, which is supposed to be the optimal solution. Inconclusion, our work supplies a first analysis of a model sensitive tospeaker-dependent characteristics, robust to defective and noisy information,and a very simple implementation which could be utilized as an alternative toeither more expensive speaker-adaptation systems or of numerous manualcorrection sessions.

Statistical Context-Dependent Units Boundary Correction for Corpus-based Unit-Selection Text-to-Speech