Temporally variable multi-aspect auditory morphing enabling extrapolation without objective and perceptual breakdown

Kawahara, Hideki; Nisimura, Ryuichi; Irino, Toshio; Morise, Masanori; Takahashi, Tôru; Banno, Hideki

doi:10.1109/icassp.2009.4960481

Cited by 37 publications

(25 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Modern voice conversion techniques such as voice morphing [13] are a crucial topic; therefore, voice morphing with the proposed system will be examined in future work.…”

Section: Discussionmentioning

confidence: 99%

PLATINUM: A method to extract excitation signals for voice synthesis system

Morise

2012

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

IntroductionRecently, vocal synthesis is a major topic, and highquality synthesis systems such as Vocaloid2 [1] were released once computer technology had developed sufficiently. To develop a high-quality vocal synthesizer, a voice synthesis system that can manipulate pitch and timbre without sound quality deterioration is required.Roughly two types of systems for voice synthesis have been proposed. One is based on the time domain pitch synchronous overlap-add (TD-PSOLA [2]), which synthesizes a voice using the short time waveform directly extracted from the input signal. The other is based on a vocoder [3], which analyzes a voice in terms of its pitch (fundamental frequency; F 0 ) and timbre (spectral envelope) and synthesizes it with the estimated parameters. TD-PSOLA and vocoders have trade offs. TD-PSOLA synthesizes voice with better quality than vocoders; however, vocoders can manipulate pitch and voice timbre independently.We propose a high-quality voice synthesis system that uses our excitation signal extraction method. A subjective evaluation experiment showed that the proposed system can synthesize a voice more naturally than with conventional vocoder-based systems.

show abstract

“…Modern voice conversion techniques such as voice morphing [13] are a crucial topic; therefore, voice morphing with the proposed system will be examined in future work.…”

Section: Discussionmentioning

confidence: 99%

PLATINUM: A method to extract excitation signals for voice synthesis system

Morise

2012

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

show abstract

“…Моделирование процесса обеспе-чивается путем раздельного представления каждой из этих составляю-щих при помощи разных средств описания. Этот подход широко приме-няется в современных системах обработки речи [26,27]. В данной работе используется аналогичный способ параметрического описания, реализо-ванный при помощи алгоритма оценки параметров периодической мо-дели с многокомпонентным гармоническим возбуждением [28].…”

Section: рис 5 использование персональной модели голоса для шумоподunclassified

Training Personal Voice Model of a Speaker with Unified Phonetic Space of Features Using Artificial Neural Network

Азаров¹,

Петровский²

2014

Тр. СПИИРАН

View full text Add to dashboard Cite

Azarov E., Petrovsky A. Training Personal Voice Model of a Speaker with Unified PhoneticSpace of Features Using Artificial Neural Network. Abstract. The paper investigates possibility of creating a personal voice model using transcribed speech samples of a specified speaker. The paper presents a practical way of building such speech model and some experimental results of applying the model to voice conversion. The model uses an artificial neural network organized as autoencoder that establishes correspondence between space of speech parameters and space of possible phonetic states, unified for any voice.

show abstract

“…This is also based on the singing-to-singing synthesis approach and is an extension of VocaListener, which deals with only pitch and dynamics. Much previous work has been done on manipulating voice timbre such as speaking voice conversion [12,13], emotional speech synthesis [14][15][16], singing voice conversion [17], and singing voice morphing [18]. However, these approaches cannot deal with intentional temporal timbre changes during singing.…”

Section: Vocalistener2: Singing Synthesis System Imitating Voice Timbmentioning

confidence: 99%

VocaListener and VocaWatcher: Imitating a human singer by using signal processing

Goto

Nakano

Kajita

et al. 2012

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we describe three singing information processing systems, VocaListener, VocaListener2, and VocaWatcher, that imitate singing expressions of the voice and face of a human singer. VocaListener can synthesize natural singing voices by analyzing and imitating the pitch and dynamics of the human singing. VocaListener2 imitates temporal timbre changes in addition to the pitch and dynamics. In synchronization with the synthesized singing voices, VocaWatcher can generate realistic facial motions of a humanoid robot, the HRP-4C, by analyzing and imitating facial motions of a human singing that are recorded by a single video camera. These systems that focus on "imitation" are not only promising for representing human-like naturalness, but also useful for providing intuitive control means.

show abstract

Temporally variable multi-aspect auditory morphing enabling extrapolation without objective and perceptual breakdown

Cited by 37 publications

References 6 publications

PLATINUM: A method to extract excitation signals for voice synthesis system

PLATINUM: A method to extract excitation signals for voice synthesis system

Training Personal Voice Model of a Speaker with Unified Phonetic Space of Features Using Artificial Neural Network

VocaListener and VocaWatcher: Imitating a human singer by using signal processing

Contact Info

Product

Resources

About