Results 31 to 40 of about 371,452 (184)
Sampling-based speech parameter generation using moment-matching networks
, 2017 This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and ...
Koriyama, Tomoki +2 more
core +1 more source
Speech Synthesis With Mixed Emotions
IEEE Transactions on Affective Computing, 2023 Emotional speech synthesis aims to synthesize human voices with various emotional effects. The current studies are mostly focused on imitating an averaged style belonging to a specific emotion type. In this paper, we seek to generate speech with a mixture of emotions at run-time.
Kun Zhou +4 more
openaire +4 more sources
HMM-based speech synthesiser using the LF-model of the glottal source [PDF]
, 2011 A major factor which causes a deterioration in speech quality in HMM-based speech synthesis is the use of a simple delta pulse signal to generate the excitation of voiced speech.
Cabral, J. +3 more
core +4 more sources
Syntezator mowy jako narzędzie wspierające pracę tłumacza
Między Oryginałem a Przekładem, 2014 The speech synthesiser as a tool supporting the job of the translator The present paper discusses the speech synthesis technology and its potential use as a tool supporting translators. The growing popularity, improving quality and ubiquity of speech
Wojciech Figiel
doaj +1 more source
Investigating the shortcomings of HMM synthesis [PDF]
, 2013 This paper presents the beginnings of a framework for formal testing of the causes of the current limited quality of HMM (Hidden Markov Model) speech synthesis.
King, Simon, Merritt, Thomas
core +1 more source
Mage - Reactive articulatory feature control of HMM-based parametric speech synthesis [PDF]
, 2013 In this paper, we present the integration of articulatory control into MAGE, a framework for realtime and interactive (reactive) parametric speech synthesis using hidden Markov models (HMMs). MAGE is based on the speech synthesis engine from HTS and uses
Astrinaki, Maria +6 more
core +1 more source
Dimensional Affective Speech Synthesis Based on Voice Conversion
Intelligent ComputingAffective speech synthesis can promote more natural human–computer interaction. Previous studies in the field of speech synthesis have used feature conversion to achieve natural affective speech.
Xin Zhang, Yaobin Wan, Wei Wang
doaj +1 more source
Reducing over-smoothness in HMM-based speech synthesis using exemplar-based voice conversion
EURASIP Journal on Audio, Speech, and Music Processing, 2017 Speech synthesis has been applied in many kinds of practical applications. Currently, state-of-the-art speech synthesis uses statistical methods based on hidden Markov model (HMM).
Gia-Nhu Nguyen, Trung-Nghia Phung
doaj +1 more source
Multi Speaker Natural Speech Synthesis Using Generative Flows
Современные информационные технологии и IT-образование, 2021 Modern speech synthesis systems generate natural speech and have high performance. Models using generative flows, among others, have shown impressive results, allowing you to form a variety of speech pronunciation from a given text.
Dmitry Obukhov
doaj +1 more source
On Using Backpropagation for Speech Texture Generation and Voice Conversion
, 2018 Inspired by recent work on neural network image generation which rely on backpropagation towards the network inputs, we present a proof-of-concept system for speech texture synthesis and voice conversion based on two mechanisms: approximate inversion of ...
Bengio, Samy +3 more
core +1 more source