Fast Griffin Lim based waveform generation strategy for text-to-speech synthesis
Sign Up to like & getrecommendations! Published in 2020 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-020-09321-7
Abstract: The performance of text-to-speech (TTS) systems heavily depends on spectrogram to waveform generation, also known as the speech reconstruction phase. The time required for the same is known as synthesis delay. In this paper, an… read more here.
Keywords: text speech; speech; speech synthesis; waveform generation ... See more keywords
The Effect of Simultaneous Text on the Recall of Noise-Degraded Speech
Sign Up to like & getrecommendations! Published in 2017 at "Journal of Experimental Psychology: Human Perception and Performance"
DOI: 10.1037/xhp0000360
Abstract: Written and spoken language utilize the same processing system, enabling text to modulate speech processing. We investigated how simultaneously presented text affected speech recall in babble noise using a retrospective recall task. Participants were presented… read more here.
Keywords: text speech; speech; degraded speech; recall ... See more keywords
The Effects of Shared e-Book Reading With Dynamic Text and Speech Output on the Single-Word Reading Skills of Young Children With Developmental Disabilities.
Sign Up to like & getrecommendations! Published in 2020 at "Language, speech, and hearing services in schools"
DOI: 10.1044/2020_lshss-20-00009
Abstract: Purpose This study investigated the use of a new software feature, namely, dynamic text with speech output, on the acquisition of single-word reading skills by six children with developmental disabilities during shared e-book reading experiences… read more here.
Keywords: children developmental; text speech; word; reading ... See more keywords
Japanese Neural Incremental Text-to-Speech Synthesis Framework With an Accent Phrase Input
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3251657
Abstract: Work in the development of neural incremental text-to-speech (iTTS), which is attracting increasing attention, has recently pursued low-latency processing by generating speech on the fly before reading complete sentences. Most current state-of-the-art iTTS systems use… read more here.
Keywords: neural incremental; text speech; speech; incremental text ... See more keywords
Incremental Text-to-Speech Synthesis Using Pseudo Lookahead With Large Pretrained Language Model
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2021.3073869
Abstract: This letter presents an incremental text-to-speech (TTS) method that performs synthesis in small linguistic units while maintaining the naturalness of output speech. Incremental TTS is generally subject to a trade-off between latency and synthetic speech… read more here.
Keywords: language model; pseudo lookahead; method; text speech ... See more keywords
A Controllable Multi-Lingual Multi-Speaker Multi-Style Text-to-Speech Synthesis With Multivariate Information Minimization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2021.3125259
Abstract: In this letter, we propose a multivariate information minimization method that disentangles three or more latent representations. We show that control factors can be disentangled by minimizing interactive dependency, which can be expressed as a… read more here.
Keywords: multi; information minimization; information; multivariate information ... See more keywords
SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2022.3226655
Abstract: Zero-shot multi-speaker text-to-speech (ZSM-TTS) models aim to generate a speech sample with the voice characteristic of an unseen speaker. The main challenge of ZSM-TTS is to increase the overall speaker similarity for unseen speakers. One… read more here.
Keywords: text speech; speech; multi speaker; speaker ... See more keywords
Distribution-Preserving Steganography Based on Text-to-Speech Generative Models
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2021.3095072
Abstract: Steganography is the art and science of hiding secret messages in public communication so that the presence of secret messages cannot be detected. There are two distribution-preserving steganographic frameworks, one is sampler-based and the other… read more here.
Keywords: text speech; preserving steganography; distribution preserving; generative models ... See more keywords
The first FOSD-tacotron-2-based text-to-speech application for Vietnamese
Sign Up to like & getrecommendations! Published in 2021 at "Bulletin of Electrical Engineering and Informatics"
DOI: 10.11591/eei.v10i2.2539
Abstract: Recently, with the development and deployment of voicebots which help to minimize personnels at call centers, text-to-speech (TTS) systems supporting English and Chinese have attracted attentions of researchers and corporates worldwide. However, there is very… read more here.
Keywords: fosd; application; tacotron based; text speech ... See more keywords
The Interaction of Cognitive Profiles and Text-to-Speech Software on Reading Comprehension of Adolescents With Reading Challenges
Sign Up to like & getrecommendations! Published in 2021 at "Journal of Special Education Technology"
DOI: 10.1177/01626434211033577
Abstract: This study utilized the Simple View of Reading (SVR) model cognitive subtypes to determine the impact of text-to-speech (TTS) software on the reading comprehension of 94 grade 8 students with reading difficulties. paired samples t… read more here.
Keywords: reading comprehension; software reading; comprehension; text speech ... See more keywords
MAKEDONKA: Applied Deep Learning Model for Text-to-Speech Synthesis in Macedonian Language
Sign Up to like & getrecommendations! Published in 2020 at "Applied Sciences"
DOI: 10.3390/app10196882
Abstract: This paper presents MAKEDONKA, the first open-source Macedonian language synthesizer that is based on the Deep Learning approach. The paper provides an overview of the numerous attempts to achieve a human-like reproducible speech, which has… read more here.
Keywords: macedonian language; text speech; model; speech ... See more keywords