Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

12.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
12.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.2K
3.2K
Air-entraining Agents01:27

Air-entraining Agents

164
Air-entraining agents improve the durability and workability of concrete in climates with frequent freezing and thawing. These agents prevent cracks by introducing small air bubbles into the mix, creating spaces accommodating water expansion when temperatures drop. The air-entraining agents lower the surface tension of water, forming stable, small air bubbles. This method is more effective than having accidental large voids, as the intentional, smaller, and evenly distributed air voids improve...
164
Auditory Pathway01:15

Auditory Pathway

6.3K
Auditory pathways constitute the complex neural circuits responsible for transmitting and interpreting auditory information from the peripheral auditory system to the brain. Sound waves are initially captured by the outer ear, funneled through the ear canal, and reach the tympanic membrane (eardrum). These vibrations are transmitted via the middle ear's ossicles to the inner ear's cochlea.
When viewed cross-sectionally, the cochlea reveals the scala vestibuli and scala tympani flanking...
6.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Effective and direct control of neural TTS prosody by removing interactions between different attributes.

Neural networks : the official journal of the International Neural Network Society·2021
Same author

Proteomic characterization of Mycobacterium tuberculosis reveals potential targets of bostrycin.

Journal of proteomics·2019
Same author

Percutaneous Transforaminal Endoscopic Discectomy Versus Microendoscopic Discectomy for Lumbar Disc Herniation: Two-Year Results of a Randomized Controlled Trial.

Spine·2019
Same author

Integrated analysis of competing endogenous RNA (ceRNA) networks in subacute stage of spinal cord injury.

Gene·2019
Same author

Enhanced hydrolysis-acidification of high-solids and low-organic-content sludge by biological thermal-alkaline synergism.

Bioresource technology·2019
Same author

Simultaneous partial nitrification, anammox and denitrification (SNAD) process for nitrogen and refractory organic compounds removal from mature landfill leachate: Performance and metagenome-based microbial ecology.

Bioresource technology·2019

Related Experiment Video

Updated: Nov 11, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.8K

Cycle consistent network for end-to-end style transfer TTS training.

Liumeng Xue1, Shifeng Pan2, Lei He2

  • 1Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China.

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a novel end-to-end Text-to-Speech (TTS) system for versatile speaking style transfer. The cycle-consistent network enhances speech quality and speaker similarity in both paired and unpaired scenarios.

Keywords:
Cycle consistentEnd-to-endSpeech synthesisStyle transferVariational autoencoder

More Related Videos

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition
12:49

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Published on: July 13, 2019

17.5K
Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique
11:39

Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique

Published on: September 7, 2022

2.4K

Related Experiment Videos

Last Updated: Nov 11, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.8K
Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition
12:49

Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition

Published on: July 13, 2019

17.5K
Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique
11:39

Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique

Published on: September 7, 2022

2.4K

Area of Science:

  • Speech synthesis
  • Machine learning
  • Artificial intelligence

Background:

  • Text-to-Speech (TTS) systems traditionally require paired data for training.
  • Speaking style transfer is challenging, especially with unpaired data.
  • Existing Variational Autoencoder (VAE) TTS models often struggle with unpaired style transfer.

Purpose of the Study:

  • To develop an end-to-end TTS system capable of effective speaking style transfer.
  • To address the limitations of paired training data in style transfer tasks.
  • To improve naturalness, speech quality, and style similarity in TTS.

Main Methods:

  • Proposed a cycle-consistent network integrated with a multi-speaker VAE TTS model.
  • Augmented the model with an unpaired path featuring a separated variational style encoder.
  • Implemented a cycle-consistent mechanism to constrain unpaired outputs without direct ground-truth targets.

Main Results:

  • Ablation studies confirmed the effectiveness of the unpaired path, separated style encoders, and cycle-consistent network.
  • The proposed approach significantly outperformed Global Style Token (GST) and VAE-based systems.
  • Achieved superior results across six style transfer categories in naturalness, speech quality, speaker identity, and style similarity.

Conclusions:

  • The developed cycle-consistent network TTS model enables high-quality speaking style transfer.
  • The unpaired path and cycle consistency are crucial for handling unpaired data effectively.
  • This method represents a significant advancement in TTS for diverse speaking style applications.