Journal Article10.1023/A:1025704800086
Optimal Utterance Selection for Unit Selection Speech Synthesis Databases
Alan W. Black,Kevin A. Lenzo +1 more
11
TL;DR: This paper describes techniques to find an optimal data set for building high quality unit-selection speech synthesis inventories and a more complex acoustic modeling technique based on the database speaker's acoustic characteristics.
read more
Abstract: This paper describes techniques to find an optimal data set for building high quality unit-selection speech synthesis inventories As the quality of unit-selection speech synthesis is dependent on the coverage of the database used in the selection, it is important to select the right data to record In this paper we describe some simple techniques as well as a more complex acoustic modeling technique based on the database speaker's acoustic characteristics Result of a simple evaluation procedure are presented justifying the technique
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Book
不思議の国のアリス = Alice's adventures in woderland
Lewis Carroll,政次 尾上 +1 more
- 01 Jan 1955
TL;DR: In this article, the authors argue that what Alice is exposed to and reacts to in Wonderland generally reflects the genre of a Bildungsroman and also specifically a feminist BildungSroman, and demonstrate how the novel also has a coming of age aspect based on feminism.
546
On Using Multiple Models for Automatic Speech Segmentation
Seung Seop Park,Nam Soo Kim +1 more
TL;DR: A novel approach to automatic speech segmentation for unit-selection based text-to-speech systems that makes use of multiple independent ASMs to produce a final boundary time-mark, and improves the percentage of boundaries that deviate less than 20 ms with respect to the reference boundary.
35
Duration modeling using DNN for Arabic speech synthesis
TL;DR: This paper compares several modeling of phoneme durations, and proposes a new approach which relies on using a set of models, each one being optimal for a given phoneme class (e.g., simple consonants, geminated consonant, short vowels, and long vowels).
19
Tone-Group F0 selection for modeling focus prominence in small-footprint speech synthesis
TL;DR: This work presents a robust unit-selection methodology for generating realistic F0 curves in cases where focus prominence is required, based on selecting Tone-Group units from commonly used prosodic corpora that are automatically transcribed as patterns of syllables.
13
Corpus design for a unit selection TtS system with application to Bulgarian
Aimilios Chalamandaris,Pirros Tsiakoulis,Spyros Raptis,Sotiris Karabetsos +3 more
- 06 Nov 2009
TL;DR: This paper presents the process of designing an efficient speech corpus for the first unit selection speech synthesis system for Bulgarian, along with some significant preliminary results regarding the quality of the resulted system.
9
References
•Book
Classification and regression trees
Leo Breiman
- 01 Jan 1983
TL;DR: The methodology used to construct tree structured rules is the focus of a monograph as mentioned in this paper, covering the use of trees as a data analysis method, and in a more mathematical framework, proving some of their fundamental properties.
22.7K
Unit selection in a concatenative speech synthesis system using a large speech database
Andrew Hunt,Alan W. Black +1 more
- 07 May 1996
TL;DR: In this paper, a state transition network is proposed to select and concatenate phonemes from a large speech database to produce a natural realisation of a target phoneme sequence predicted from text which is annotated with prosodic and phonetic context information.
•Dissertation
Festival Speech Synthesis System
Alan W. Black,Paul Taylor,Richard Caley +2 more
- 01 Jan 2000
400
Related Papers (5)
Mehryar Mohri,Cyril Allauzen,Michael Riley +2 more
- 21 Jul 2004
Ivan Bulyko,Mari Ostendorf +1 more
- 01 Jan 2002