2 |
An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Persuasive synthetic speech : voice perception and user behaviour
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Unsupervised neural and Bayesian models for zero-resource speech processing
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Statistical parametric speech synthesis using conversational data and phenomena
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Overcoming the limitations of statistical parametric speech synthesis
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Improving Trajectory Modelling for DNN-based Speech Synthesis by using Stacked Bottleneck Features and Minimum Generation Error Training ...
|
|
|
|
Abstract:
We propose two novel techniques --- stacking bottleneck features and minimum generation error training criterion --- to improve the performance of deep neural network (DNN)-based speech synthesis. The techniques address the related issues of frame-by-frame independence and ignorance of the relationship between static and dynamic features, within current typical DNN-based synthesis frameworks. Stacking bottleneck features, which are an acoustically--informed linguistic representation, provides an efficient way to include more detailed linguistic context at the input. The minimum generation error training criterion minimises overall output trajectory error across an utterance, rather than minimising the error per frame independently, and thus takes into account the interaction between static and dynamic features. The two techniques can be easily combined to further improve performance. We present both objective and subjective results that demonstrate the effectiveness of the proposed techniques. The subjective ... : submitted to IEEE/ACM Transactions on Audio, Speech and Language Processing 2016 (AQ) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Neural and Evolutionary Computing cs.NE; Sound cs.SD
|
|
URL: https://dx.doi.org/10.48550/arxiv.1602.06727 https://arxiv.org/abs/1602.06727
|
|
BASE
|
|
Hide details
|
|
9 |
DNN-based Speech Synthesis for Indian Languages from ASCII text ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Speech segmentation and speaker diarisation for transcription and translation
|
|
|
|
BASE
|
|
Show details
|
|
15 |
The listening talker: A review of human and algorithmic context-induced modifications of speech
|
|
|
|
In: ISSN: 0885-2308 ; EISSN: 1095-8363 ; Computer Speech and Language ; https://hal.archives-ouvertes.fr/hal-00874986 ; Computer Speech and Language, Elsevier, 2014, 28 (2), pp.543-571. ⟨10.1016/j.csl.2013.08.003⟩ (2014)
|
|
BASE
|
|
Show details
|
|
16 |
EUSTACE : Edinburgh University speech timing archive and corpus of English
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Measuring a decade of progress in Text-to-Speech ; Evaluando una década de avances en la conversión texto-habla
|
|
|
|
In: Loquens; Vol. 1 No. 1 (2014); e006 ; Loquens; Vol. 1 Núm. 1 (2014); e006 ; 2386-2637 ; 10.3989/loquens.2014.v1.i1 (2014)
|
|
BASE
|
|
Show details
|
|
18 |
Feature analysis for discriminative confidence estimation in spoken term detection
|
|
|
|
BASE
|
|
Show details
|
|
19 |
A Comparison of Open-Source Segmentation Architectures for Dealing with Imperfect Data from the Media in Speech Synthesis
|
|
|
|
BASE
|
|
Show details
|
|
20 |
The listening talker : a review of human and algorithmic context-induced modifications of speech
|
|
|
|
BASE
|
|
Show details
|
|
|
|