Hierarchical representation and estimation of prosody using continuous wavelet transform

85 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Survey on Neural Speech Synthesis (2021, background): “[324] demonstrate that hierarchical structures of prosody intrinsically exist in spoken languages.”
Investigating the Utility of Surprisal from Large Language Models for Speech Synthesis Prosody (2023, background): “As also noted in [20], the language models naturally tend to assign low surprisal for the phrase endings and first names instead of surnames, contradicting the typical English pattern of assigning stress to the final word.”
Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis (2020, background): “It has been shown that hierarchical structures of prosody intrinsically exist in spoken language [12].”
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations (2019, methodology): “ing acoustic features seem to provide better performance for the unsupervised detection of prominences in speech (Suni et al., 2017; Wang and Narayanan, 2007; Kakouros and Räsänen, 2016), with state-of-the-art results reaching high level of”