Parametric representation for singing voice synthesis: A comparative evaluation

Babacan, Onur; Drugman, Thomas; Raitio, Tuomo; Erro, Daniel; Dutoit, Thierry

doi:10.1109/icassp.2014.6854063

Cited by 8 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the amount of degradation may differ markedly between speakers (voices), and one vocoder or another may perform better or worse for any particular speakers; cf. (Babacan, Drugman, Raitio, Erro & Dutoit 2014) for singing. These quality variations suggest a notion of "vocodability", the consequence of which is a (perhaps undesirable) bias when selecting a speaker for a TTS corpus, towards a voice that suffers minimal degradation at the hands of the vocoder.…”

Section: Vocodingmentioning

confidence: 99%

Analysing Shortcomings of Statistical Parametric Speech Synthesis

Henter¹,

King²,

Merritt³

et al. 2018

Preprint

View full text Add to dashboard Cite

This is a draft chapter for the book "Natural Speech Technology: Statistical and Machine Learning Approaches to Speech Recognition and Synthesis".The chapter text was mainly written prior to and during November 2016, and reflects the shape and general understanding of statistical speech synthesis at that time. The draft was edited in July 2017 for length and edited again in July 2018 to function as a stand-alone document, as presented here. This version was compiled on July 31, 2018.

show abstract

Section: Vocodingmentioning

confidence: 99%

Analysing Shortcomings of Statistical Parametric Speech Synthesis

Henter¹,

King²,

Merritt³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…The model training follows the speaker dependent singing synthesis system using STRAIGHT [17] for feature extraction and synthesis. [18] analysed the analysis/re-synthesis quality of different parametric representations for singing speech, where STRAIGHT achieved a good performance. It would also be interesting to evaluate statistical parametric opera singing synthesis with different vocoders, which is however out of the scope of this paper.…”

Section: Acoustic Modellingmentioning

confidence: 99%

Development of a statistical parametric synthesis system for operatic singing in German

Pucher¹,

Villavicencio²,

Yamagishi³

2016

9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)

View full text Add to dashboard Cite

In this paper we describe the development of a Hidden Markov Model (HMM) based synthesis system for operatic singing in German, which is an extension of the HMM-based synthesis system for popular songs in Japanese and English called "Sinsy". The implementation of this system consists of German text analysis, lexicon and Letter-To-Sound (LTS) conversion, and syllable duplication, which enables us to convert a German MusicXML input into context-dependent labels for acoustic modelling. Using the front-end, we develop two operatic singing voices, female mezzo-soprano and male bass voices, based on our new database, which consists of singing data of professional opera singers based in Vienna. We describe the details of the database and the recording procedure that is used to acquire singing data of four opera singers in German. For HMM training, we adopt a singer (speaker)-dependent training procedure. For duration modelling we propose a simple method that hierarchically constrains note durations by the overall utterance duration and then constrains phone durations by the synthesised note duration. We evaluate the performance of the voices with two vibrato modelling methods that have been proposed in the literature and show that HMM-based vibrato modelling can improve the overall quality.

show abstract

“…F 0 was estimated using the Summation of the Residual Harmoncis (SRH) algorithm [16]. TE is here required as standard cepstral analysis was reported in [12] to be inappropriated for singing voice analysis. TE was estimated using the COVAREP toolkit [17].…”

Section: A Experimental Protocolmentioning

confidence: 99%

“…In [11], the use of a dynamic MVF was even found to be slightly preferred over the multiband approach. While current methods of MVF estimation seem to be efficient in speech, some issues were reported in [12] for the synthesis of singing voices. For highpitched voices, MVF was observed to be underestimated which led to an excessive amount of noise after synthesis.…”

Section: Introductionmentioning

confidence: 99%

Maximum Voiced Frequency Estimation: Exploiting Amplitude and Phase Spectra

Drugman

Stylianou

2014

IEEE Signal Process. Lett.

Self Cite

View full text Add to dashboard Cite

Maximum Voiced Frequency (MVF) is used in various speech models as the spectral boundary separating periodic and aperiodic components during the production of voiced sounds. Recent studies have shown that its proper estimation and modeling enhance the quality of statistical parametric speech synthesizers. Contrastingly, these same methods of MVF estimation have been reported to degrade the performance of singing voice synthesizers. This paper proposes a new approach for MVF estimation which exploits both amplitude and phase spectra. It is shown that phase conveys relevant information about the harmonicity of the voice signal, and that it can be jointly used with features derived from the amplitude spectrum. This information is further integrated into a maximum likelihood criterion which provides a decision about the MVF estimate. The proposed technique is compared to two state-of-the-art methods, and shows a superior performance in both objective and subjective evaluations. Perceptual tests indicate a drastic improvement in high-pitched voices.

show abstract

Parametric representation for singing voice synthesis: A comparative evaluation

Cited by 8 publications

References 30 publications

Analysing Shortcomings of Statistical Parametric Speech Synthesis

Analysing Shortcomings of Statistical Parametric Speech Synthesis

Development of a statistical parametric synthesis system for operatic singing in German

Maximum Voiced Frequency Estimation: Exploiting Amplitude and Phase Spectra

Contact Info

Product

Resources

About