Augmented speech production based on real-time statistical voice conversion

Toda, Tomoki

doi:10.1109/globalsip.2014.7032186

Cited by 18 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Voice conversion (VC) is one of the potential techniques enabling speakers to produce speech sounds beyond their physical constraints [1]. VC research was originally started to develop a speaker individuality conversion technique enabling a source speaker to change his/her speaker individuality to that of another target speaker while preserving the linguistic content [2].…”

Section: Introductionmentioning

confidence: 99%

sprocket: Open-Source Voice Conversion Software

Kobayashi¹,

Toda²

2018

EasyChair Preprints

Self Cite

View full text Add to dashboard Cite

Statistical voice conversion (VC) is a technique to convert specific non-or paralinguistic information while keeping linguistic information unchanged, and speaker conversion has been studied as a typical application of VC for a few decades. To better understand various VC techniques using a freely available common dataset, the Voice Conversion Challenge (VCC) was launched in 2016 and the 2nd challenge was held in 2018. As one of the baseline systems for VCC 2018, we developed open-source VC software called "sprocket", in which not only conventional techniques, such as a trajectory-based conversion method using a Gaussian mixture model (GMM) and a vocoderbased conversion framework but also recently developed techniques, such as a vocoder-free VC framework, have been implemented. Using sprocket, it is possible to 1) easily reproduce converted voices using the VCC datasets and 2) develop VC systems using other parallel speech datasets with fundamental VC functions, such as acoustic feature extraction, time alignment between the source and target features, GMM training, feature conversion, and waveform generation. In this paper, we describe 1) the technical details and use of sprocket, 2) the development of the baseline systems for the HUB and SPOKE tasks of VCC 2018 using sprocket, and 3) the performance of sprocket as a VC system by demonstrating results for our developed baseline systems in VCC 2018.

show abstract

Section: Introductionmentioning

confidence: 99%

sprocket: Open-Source Voice Conversion Software

Kobayashi¹,

Toda²

2018

EasyChair Preprints

Self Cite

View full text Add to dashboard Cite

show abstract

“…Voice conversion (VC) is a potential technique to enable us for producing speech sounds beyond our own physical constraints [1]. VC research was originally started to implement the speaker conversion which enables a source speaker to transform his/her speaker individuality into another target speaker while preserving the linguistic content [2].…”

Section: Introductionmentioning

confidence: 99%

Statistical Voice Conversion with WaveNet-Based Waveform Generation

et al. 2017

Self Cite

View full text Add to dashboard Cite

This paper presents a statistical voice conversion (VC) technique with the WaveNet-based waveform generation. VC based on a Gaussian mixture model (GMM) makes it possible to convert the speaker identity of a source speaker into that of a target speaker. However, in the conventional vocoding process, various factors such as F0 extraction errors, parameterization errors and over-smoothing effects of converted feature trajectory cause the modeling errors of the speech waveform, which usually bring about sound quality degradation of the converted voice. To address this issue, we apply a direct waveform generation technique based on a WaveNet vocoder to VC. In the proposed method, first, the acoustic features of the source speaker are converted into those of the target speaker based on the GMM. Then, the waveform samples of the converted voice are generated based on the WaveNet vocoder conditioned on the converted acoustic features. In this paper, to investigate the modeling accuracies of the converted speech waveform, we compare several types of the acoustic features for training and synthesizing based on the WaveNet vocoder. The experimental results confirmed that the proposed VC technique achieves higher conversion accuracy on speaker individuality with comparable sound quality compared to the conventional VC technique.

show abstract

“…With the help of improvement on artificial intelligence [9][10][11], the part of voice selection, understanding and re-express becomes more and more easily [12,13]. Therefore, the output of the voice changer could be in voice, or could be in words pressed on TV [14,15]. With regards to the camera, it can be professional ones hanging on the ceil and rotating round and round.…”

Section: B Hardware Componentsmentioning

confidence: 99%

A New Double-Blind System Applied at College Student Interview

Qiao¹

2019

Proceedings of the 2019 International Conference on Contemporary Education and Society Development (ICCESD 2019)

View full text Add to dashboard Cite

With the development of education technique, interview section is playing more and more important role in high education. In order to make the interview more fair-minded, and keep the emotion influence or any unjust factors away, this paper proposed a new double-blind system and its usage guidance. The system consists of room arrangement, hardware components, and software components. The operation guidance was divided into four steps to help the whole interview procedure go smoothly and fairly. The result of this paper kept the interviewee and the interviewer from recognizing each other by applying voice changer, camera and the like. It's simple, low cost and easy to operate, so it can be popularized to more areas than college interview. With the emergence of more and more advanced information devices and new technologies, the system and operation method will be refreshed shortly in the future.

show abstract

Augmented speech production based on real-time statistical voice conversion

Cited by 18 publications

References 34 publications

sprocket: Open-Source Voice Conversion Software

sprocket: Open-Source Voice Conversion Software

Statistical Voice Conversion with WaveNet-Based Waveform Generation

A New Double-Blind System Applied at College Student Interview

Contact Info

Product

Resources

About