Generating synthetic speech prosody with lazy learning in tree structures

6Citations
Citations of this article
69Readers
Mendeley users who have this article in their library.

Abstract

We present ongoing work on prosody prediction for speech synthesis. This approach considers sentences as tree structures and infers the prosody from a corpus of such structures using machine learning techniques. The prediction is achieved from the prosody of the closest sentence of the corpus through tree similarity measurements, using either the nearest neighbour algorithm or an analogy-based approach. We introduce two different tree structure representations, the tree similarity metrics considered, and then we discuss the different prediction methods. Experiments are currently under process to qualify this approach.

References Powered by Scopus

The String-to-String Correction Problem

2326Citations
N/AReaders
Get full text

Performance structures: A psycholinguistic and linguistic appraisal

307Citations
N/AReaders
Get full text

The tree-to-tree editing problem

287Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Analogical dissimilarity: Definition, algorithms and two experiments in machine learning

123Citations
N/AReaders
Get full text

Synthesising hyperarticulation in unit selection TTS

2Citations
N/AReaders
Get full text

Prosodic modelling for Croatian speech synthesis

0Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Blin, L., & Miclet, L. (2000). Generating synthetic speech prosody with lazy learning in tree structures. In Proceedings of the 4th Conference on Computational Natural Language Learning, CoNLL 2000 and of the 2nd Learning Language in Logic Workshop, LLL 2000 - Held in cooperation with ICGI 2000 (pp. 87–90). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1117601.1117620

Readers over time

‘10‘11‘12‘19‘20‘21‘22‘23‘24‘2507142128

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 19

59%

Researcher 8

25%

Professor / Associate Prof. 3

9%

Lecturer / Post doc 2

6%

Readers' Discipline

Tooltip

Computer Science 25

76%

Linguistics 5

15%

Social Sciences 2

6%

Philosophy 1

3%

Save time finding and organizing research with Mendeley

Sign up for free
0