Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Cloning of Dolly the Sheep

Cloning of Dolly the Sheep

The first successfully cloned mammal was Dolly, a sheep, born on 5th July 1996 at Roslin Institute, Scotland. The cloned sheep was named after the American singer Dolly Parton. Dolly lived for seven years and died of respiratory complications, which is speculated to be due to the actual age of her DNA. Because the DNA in cloned cells belongs to an older individual, the cloned individual’s life expectancy may be affected. Indeed, analysis of Dolly’s DNA revealed shorter...

Reconstruction of Signal using Interpolation

Reconstruction of Signal using Interpolation

Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...

Facial Feedback Hypothesis

Facial Feedback Hypothesis

Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...

Reproductive Cloning

Reproductive Cloning

Reproductive cloning is the process of producing a genetically identical copy—a clone—of an entire organism. While clones can be produced by splitting an early embryo—similar to what happens naturally with identical twins—cloning of adult animals is usually done by a process called somatic cell nuclear transfer (SCNT).
Somatic Cell Nuclear Transfer
In SCNT, an egg cell is taken from an animal and its nucleus is removed, creating an enucleated egg. Then a somatic...

Linear Approximation in Frequency Domain

Linear Approximation in Frequency Domain

Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....

Downsampling

Downsampling

When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...

You might also read

Related Articles

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

Sort by

Same author

Systematic evaluation of membrane-camouflaged nanoparticles in neutralizing Clostridium perfringens ε-toxin.

Journal of nanobiotechnology·2023

Same author

Quantitative and causal analysis for inflammatory genes and the risk of Parkinson's disease.

Frontiers in immunology·2023

Same author

Health and Wellness Tourists' Motivation and Behavior Intention: The Role of Perceived Value.

International journal of environmental research and public health·2023

Same author

Magnetorheological and Viscoelastic Behaviors in an Fe-Based Amorphous Magnetic Fluid.

Materials (Basel, Switzerland)·2023

Same author

Foodborne Carbon Dot Exposure Induces Insulin Resistance through Gut Microbiota Dysbiosis and Damaged Intestinal Mucus Layer.

ACS nano·2023

Same author

A Two-Stage End-to-End Deep Learning Framework for Pathologic Examination in Skin Tumor Diagnosis.

The American journal of pathology·2023

Search research articles

Related Experiment Video

Updated: Aug 24, 2025

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

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

Published on: August 9, 2024

A Voice Cloning Method Based on the Improved HiFi-GAN Model.

Zeyu Qiu¹, Jun Tang¹, Yaxin Zhang²

¹Information Engineering University, Zhengzhou 450001, China.

Computational Intelligence and Neuroscience

|October 21, 2022

Summary

This summary is machine-generated.

This study introduces an improved HiFi-GAN model for voice cloning, enhancing speaker characteristics and inference speed. The new method achieves higher voice similarity and quality compared to existing systems.

More Related Videos

Synthetic, Multi-Layer, Self-Oscillating Vocal Fold Model Fabrication

Synthetic, Multi-Layer, Self-Oscillating Vocal Fold Model Fabrication

Published on: December 2, 2011

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Published on: January 5, 2024

Related Experiment Videos

Last Updated: Aug 24, 2025

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

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

Published on: August 9, 2024

Synthetic, Multi-Layer, Self-Oscillating Vocal Fold Model Fabrication

Synthetic, Multi-Layer, Self-Oscillating Vocal Fold Model Fabrication

Published on: December 2, 2011

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Published on: January 5, 2024

Area of Science:

Artificial Intelligence
Speech Synthesis
Machine Learning

Background:

Voice cloning, a Text-to-Speech (TTS) service, aims to synthesize personal voices from limited speech samples.
Existing d-vector methods in Tacotron 2-based TTS have limitations in capturing complete utterance voice characteristics, impacting voice cloning similarity.
WaveNet vocoder offers high quality but sacrifices speech generation speed.

Purpose of the Study:

To develop a voice cloning method that balances model parameters, inference speed, and voice quality.
To improve the accuracy and efficiency of voice cloning using an enhanced HiFi-GAN architecture.

Main Methods:

Utilized x-vector as an embedding vector to enhance speaker characterization in the speaker encoder.
Implemented a competitive multiscale convolution strategy for processing Mel spectrum input in the HiFi-GAN vocoder.
Replaced standard 1D convolutions with 1D depth-wise separable convolutions to reduce parameters and increase inference speed.

Main Results:

The improved HiFi-GAN model reduced vocoder parameters by 68.58% and increased inference speed by 11.84% (GPU) and 30.99% (CPU).
Marginal improvements in voice quality were observed, with MOS increasing by 0.13 and PESQ by 0.11.
The proposed model, combined with x-vector embedding, achieved the highest scores across all models and test sets for voice cloning.

Conclusions:

The improved HiFi-GAN model demonstrates superior performance and compatibility for voice cloning tasks.
The integration of x-vector embedding further enhances the model's ability to capture speaker characteristics accurately.
This approach offers a promising solution for efficient and high-quality voice cloning.