Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

speech-2

Voice Cloning

3260 papers • 126 benchmarks • 313 datasets

Voice cloning is a highly desired feature for personalized speech interfaces. Neural voice cloning system learns to synthesize a person’s voice from only a few audio samples.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in voice-cloning-6

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find voice-cloning-6 models and implementations

PaddlePaddle/PaddleSpeech

3 papers 9,815

Datasets

GneutralSpeech Female

GneutralSpeech Female

GneutralSpeech Male

GneutralSpeech Male

Subtasks

No subtasks available.

Most implemented papers

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

Z. Chen, Ruoming Pang, Ron J. Weiss, Yu Zhang, Ye Jia, Yonghui Wu, Quan Wang, I. López-Moreno, Jonathan Shen, Fei Ren, Patrick Nguyen•Thu May 31 2018

It is shown that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.

923

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

PaddlePaddle/DeepSpeech

2 papers 9,821

0

Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

Z. Chen, Ron J. Weiss, H. Zen, Yu Zhang, Ye Jia, Yonghui Wu, R. Skerry-Ryan, A. Rosenberg, B. Ramabhadran•Mon Jul 08 2019

A multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages and be able to transfer voices across languages, e.g. English and Mandarin.

203 0

ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech

Peng Fei Zhu, Shuohuan Wang, Yu Sun, Hua Wu, Richard He Bai, Renjie Zheng, Junkun Chen, Liang Huang, Tian Yuan, Zeyu Chen, Xiaoran Fan, Chao Pang•Sun Nov 06 2022

A speech-text joint pretraining framework, where the spectrogram and the phonemes given a speech example and its transcription areMasked to reconstruct the masked parts of the input in different languages, which shows great improvements over speaker-embedding-based multi-speaker TTS methods.

1 0

Neural Voice Cloning with a Few Samples

Jitong Chen, Yanqi Zhou, Sercan Ö. Arik, Wei Ping, Kainan Peng•Tue Feb 13 2018

While speaker adaptation can achieve better naturalness and similarity, the cloning time or required memory for the speaker encoding approach is significantly less, making it favorable for low-resource deployment.

427 0

One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech

Ondrej Dusek, Tomás Nekvinda•Sun Aug 02 2020

An approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding mult bilingual speech using more languages and less training data than previous approaches is introduced.

60 0

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

Pat Pataranutaporn, Yimeng Liu, Misha Sra, P. Maes, Pulkit Tandon, Shubham Chandak, Anesu M. Mapuranga, T. Weissman•Fri Jun 25 2021

A novel video compression pipeline, called Txt2Vid, is presented, which dramatically reduces data transmission rates by compressing webcam videos to a text transcript, and achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders).

31 0

Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech

Hung-yi Lee, Chien-yu Huang, C. Chien, Jheng-hao Lin, Po-chun Hsu•Fri Mar 05 2021

This work investigates different speaker representations and proposed to integrate pretrained and learnable speaker representations to find the embedding pretrained by voice conversion achieves the best performance.

77 0

Building Bilingual and Code-Switched Voice Conversion with Limited Training Data Using Embedding Consistency Loss

Ming Li, Yaogen Yang, Haozhe Zhang, Xiaoyi Qin, Shanshan Liang, Huahua Cui, Mingyang Xu•Wed Apr 21 2021

A parallel non-autoregressive network to achieve bilingual and code-switched voice conversion for multiple speakers when there are only mono-lingual corpora for each language is described.

4 0

Discovery of Single Independent Latent Variable

Uri Shaham•Mon Oct 11 2021

This work considers data given as an invertible mixture of two statistically independent components and assumes that one of the components is observed while the other is hidden, and proposes an autoencoder equipped with a discriminator to recover the hidden component.

4 0

Adding a benchmark result helps the community track progress.

Voice Cloning | State-of-the-Art