Voice Conversion for TTS Systems with Tuning on the Target Speaker Based on GMM

Voice Conversion Across Arbitrary Speakers Based on a Single Target-Speaker Utterance

10.21437/interspeech.2018-1504 ◽

2018 ◽

Cited By ~ 8

Author(s):

Songxiang Liu ◽

Jinghua Zhong ◽

Lifa Sun ◽

Xixin Wu ◽

Xunying Liu ◽

...

Keyword(s):

Voice Conversion ◽

Single Target ◽

Target Speaker

Download Full-text

Comprehensive Source-Target Speaker Voice Conversion Analysis

International Journal of Simulation Systems Science & Technology ◽

10.5013/ijssst.a.15.06.05 ◽

2020 ◽

Author(s):

He Pan ◽

Yangjie Wei ◽

Nan Guan ◽

Yi Wang

Keyword(s):

Voice Conversion ◽

Target Speaker

Download Full-text

Effects of Sinusoidal Model on Non-Parallel Voice Conversion with Adversarial Learning

Applied Sciences ◽

10.3390/app11167489 ◽

2021 ◽

Vol 11 (16) ◽

pp. 7489

Author(s):

Mohammed Salah Al-Radhi ◽

Tamás Gábor Csapó ◽

Géza Németh

Keyword(s):

Speech Processing ◽

Voice Conversion ◽

Training Dataset ◽

Generative Adversarial Network ◽

Sinusoidal Model ◽

Time Alignment ◽

Adversarial Network ◽

Training Examples ◽

Speaking Style ◽

Target Speaker

Voice conversion (VC) transforms the speaking style of a source speaker to the speaking style of a target speaker by keeping linguistic information unchanged. Traditional VC techniques rely on parallel recordings of multiple speakers uttering the same sentences. Earlier approaches mainly find a mapping between the given source–target speakers, which contain pairs of similar utterances spoken by different speakers. However, parallel data are computationally expensive and difficult to collect. Non-parallel VC remains an interesting but challenging speech processing task. To address this limitation, we propose a method that allows a non-parallel many-to-many voice conversion by using a generative adversarial network. To the best of the authors’ knowledge, our study is the first one that employs a sinusoidal model with continuous parameters to generate converted speech signals. Our method involves only several minutes of training examples without parallel utterances or time alignment procedures, where the source–target speakers are entirely unseen by the training dataset. Moreover, empirical study is carried out on the publicly available CSTR VCTK corpus. Our conclusions indicate that the proposed method reached the state-of-the-art results in speaker similarity to the utterance produced by the target speaker, while suggesting important structural ones to be further analyzed by experts.

Download Full-text

Noise-Robust Voice Conversion Using High-Quefrency Boosting via Sub-Band Cepstrum Conversion and Fusion

Applied Sciences ◽

10.3390/app10010151 ◽

2019 ◽

Vol 10 (1) ◽

pp. 151

Author(s):

Xiaokong Miao ◽

Meng Sun ◽

Xiongwei Zhang ◽

Yimin Wang

Keyword(s):

Short Term Memory ◽

Training Data ◽

Voice Conversion ◽

Noisy Input ◽

Mean And Variance ◽

Natural Target ◽

Noise Robust ◽

The Impact ◽

Target Speaker

This paper presents a noise-robust voice conversion method with high-quefrency boosting via sub-band cepstrum conversion and fusion based on the bidirectional long short-term memory (BLSTM) neural networks that can convert parameters of vocal tracks of a source speaker into those of a target speaker. With the implementation of state-of-the-art machine learning methods, voice conversion has achieved good performance given abundant clean training data. However, the quality and similarity of the converted voice are significantly degraded compared to that of a natural target voice due to various factors, such as limited training data and noisy input speech from the source speaker. To address the problem of noisy input speech, an architecture of voice conversion with statistical filtering and sub-band cepstrum conversion and fusion is introduced. The impact of noises on the converted voice is reduced by the accurate reconstruction of the sub-band cepstrum and the subsequent statistical filtering. By normalizing the mean and variance of the converted cepstrum to those of the target cepstrum in the training phase, a cepstrum filter was constructed to further improve the quality of the converted voice. The experimental results showed that the proposed method significantly improved the naturalness and similarity of the converted voice compared to the baselines, even with the noisy inputs of source speakers.

Download Full-text

U2-VC: one-shot voice conversion using two-level nested U-structure

EURASIP Journal on Audio Speech and Music Processing ◽

10.1186/s13636-021-00226-3 ◽

2021 ◽

Vol 2021 (1) ◽

Author(s):

Fangkun Liu ◽

Hui Wang ◽

Renhua Peng ◽

Chengshi Zheng ◽

Xiaodong Li

Keyword(s):

Identity Transformation ◽

Voice Conversion ◽

Time Frequency ◽

Multi Scale ◽

Wide Range ◽

Subjective Measurements ◽

The Voice ◽

Content Information ◽

Target Speaker ◽

Made In

AbstractVoice conversion is to transform a source speaker to the target one, while keeping the linguistic content unchanged. Recently, one-shot voice conversion gradually becomes a hot topic for its potentially wide range of applications, where it has the capability to convert the voice from any source speaker to any other target speaker even when both the source speaker and the target speaker are unseen during training. Although a great progress has been made in one-shot voice conversion, the naturalness of the converted speech remains a challenging problem. To further improve the naturalness of the converted speech, this paper proposes a two-level nested U-structure (U2-Net) voice conversion algorithm called U2-VC. The U2-Net can extract both local feature and multi-scale feature of log-mel spectrogram, which can help to learn the time-frequency structures of the source speech and the target speech. Moreover, we adopt sandwich adaptive instance normalization (SaAdaIN) in decoder for speaker identity transformation to retain more content information of the source speech while maintaining the speaker similarity between the converted speech and the target speech. Experiments on VCTK dataset show that U2-VC outperforms many SOTA approaches including AGAIN-VC and AdaIN-VC in terms of both objective and subjective measurements.

Download Full-text

Vowels and Prosody Contribution in Neural Network Based Voice Conversion Algorithm with Noisy Training Data

European Journal of Engineering Research and Science ◽

10.24018/ejers.2020.5.3.1802 ◽

2020 ◽

Vol 5 (3) ◽

pp. 229-233

Author(s):

Olaide Ayodeji Agbolade

Keyword(s):

Neural Network ◽

Significant Contribution ◽

Linear Prediction ◽

Feedforward Neural Network ◽

Training Data ◽

Voice Conversion ◽

Conversion Model ◽

The Voice ◽

Average Noise Level ◽

Target Speaker

This research presents a neural network based voice conversion model. While it is a known fact that voiced sounds and prosody are the most important component of the voice conversion framework, what is not known is their objective contributions particularly in a noisy and uncontrolled environment. This model uses a 3 layer feedforward neural network to map the Linear prediction analysis coefficients of a source speaker to the acoustic vector space of the target speaker with a view to objectively determine the contributions of the voiced, unvoiced and supra-segmental components of sounds to the voice conversion model. Results showed that vowels “a”, “i”, “o” have the most significant contribution in the conversion success. The voiceless sounds were also found to be most affected by the noisy training data. An average noise level of 40 dB above the noise floor were found to degrade the voice conversion success by 55.14 percent relative to the voiced sounds. The result also show that for cross-gender voice conversion, prosody conversion is more significant in scenarios where a female is the target speaker.

Download Full-text

Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning

Advances in Multimedia ◽

10.1155/2018/5158164 ◽

2018 ◽

Vol 2018 ◽

pp. 1-14

Author(s):

XueTing Wang ◽

Cong Jin ◽

Wei Zhao

Keyword(s):

Speech Synthesis ◽

Control Model ◽

Voice Conversion ◽

Chinese Opera ◽

Wide Range ◽

Voice Control ◽

Music Generation ◽

Beijing Opera ◽

The Voice ◽

Target Speaker

Speech synthesis is an important research content in the field of human-computer interaction and has a wide range of applications. As one of its branches, singing synthesis plays an important role. Beijing Opera is a famous traditional Chinese opera, and it is called Chinese quintessence. The singing of Beijing Opera carries some features of speech but it has its own unique pronunciation rules and rhythms which differ from ordinary speech and singing. In this paper, we propose three models for the synthesis of Beijing Opera. Firstly, the speech signals of the source speaker and the target speaker are extracted by using the straight algorithm. And then through the training of GMM, we complete the voice control model to input the voice to be converted and output the voice after the voice conversion. Finally, by modeling the fundamental frequency, duration, and frequency separately, a melodic control model is constructed using GAN to realize the synthesis of the Beijing Opera fragment. We connect the fragments and superimpose the background music to achieve the synthesis of Beijing Opera. The experimental results show that the synthesized Beijing Opera has some audibility and can basically complete the composition of Beijing Opera. We also extend our models to human-AI cooperative music generation: given a target voice of human, we can generate a Beijing Opera which is sung by a new target voice.

Download Full-text