Unsupervised Prosodic Labeling of Speech Synthesis Databases Using Context-Dependent HMMs

IEICE Transactions on Information and Systems - Japan
doi 10.1587/transinf.e97.d.1449
Full Text
Abstract

Available in full text

Date
Authors
Publisher

Institute of Electronics, Information and Communications Engineers (IEICE)

Related search

Unsupervised Stress Information Labeling Using Gaussian Process Latent Variable Model for Statistical Speech Synthesis

2016English

Audiovisual-To-Articulatory Speech Inversion Using HMMs

2007English

Paragraph-Based Prosodic Cues for Speech Synthesis Applications

2016English

Towards Automatic Extraction of Prosodic Patterns for Speech Synthesis

2014English

Unsupervised Speaker Adaptation for DNN-based Speech Synthesis Using Input Codes

2018English

Unsupervised Adaptation of Categorical Prosody Models for Prosody Labeling and Speech Recognition

IEEE Transactions on Audio, Speech, and Language Processing
2009English

Prosodic Models, Automatic Speech Understanding, and Speech Synthesis: Towards the Common Ground?

The Integration of Phonetic Knowledge in Speech Technology
2005English

Usable Speech Detection Using a Context Dependent Gaussian Mixture Model Classifier

English

Prosodic Analysis of Attention-Drawing Speech

2017English

Amanote Research

Note-taking for researchers

Follow Amanote

© 2025 Amaplex Software S.P.R.L. All rights reserved.

Privacy PolicyRefund Policy