CoChat

Group Sparse Representation With WaveNet Vocoder Adaptation for Spectrum and Prosody Conversion

Sisman, Berrak, Zhang, Mingyang, Li, Haizhou · 2019 · IEEE/ACM Transactions on Audio, Speech, and Language Processing

The DOI matches its Crossref record; 68 of the 76 references it cites were found in a registry or an index.

Abstract

The statistical approach to voice conversion typically consists of a feature conversion module followed by a vocoder. So far, the feature conversion studies are mainly focused on the conversion of spectrum. However, speaker identity is also characterized by prosodic features, such as fundamental frequency F0 and energy contour among others. In this paper, we study the transformation of speaker characteristics both in terms of spectrum and prosody. We propose two novel techniques that effectively use a limited amount of source-target training data and leverage a large general speech corpus to improve the voice conversion quality. First, we study the phonetic sparse representation under the group sparsity mathematical formulation. We use phonetic posteriorgrams PPGs together with spectral and prosody features to form tandem feature in the phonetic dictionary. The tandem feature allow us to estimate an activation matrix that is less dependent on source speakers, thus providing a better voice conversion quality. Second, we study the use of WaveNet vocoder that can be trained on general speech corpus from multiple speakers and adapted on target speaker data to improve the vocoding quality. We benefit from the large general speech databases that are used to train the PPG generator, and the WaveNet vocoder. The experiments show that the proposed conversion framework outperforms the traditional spectrum and prosody conversion techniques in both objective and subjective evaluations.

Overview

Integrity signals

Registry

Crossref · 10.1109/taslp.2019.2910637

Cites

68 of 68 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 68 references

Research works printed but not linked: 4

  1. lifa, 0, Phonetic posteriorgrams for many-to-one voice conversion without parallel data training, Proc IEEE Int Conf Multimedia Expo, 1
  2. bolinger, 1962, Intonation as a universal, Int COngr Linguists Cambridge
  3. furui, 2000, Digital speech processing, synthesis, and recognition(revised and expanded), Digital Speech Processing Synthesis and Recognition
  4. wu, 0, Examplar-based voice conversion using non-negative spectrogram deconvolution, Proc ISCA Speech Synthesis Workshop

Cited by

See all 52

Metadata

Authors
Sisman, B., Zhang, M., & Li, H.
Affiliations
National University of Singapore (SG)
Venue
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Published
2019-06
Volume
27
Issue
6
Pages
1085-1097
ISSN
  • 2329-9290 (ISSN-L)
  • 2329-9304
OpenAlex
W2941094131
Cited by
52
References
76
Citations by year
2026: 1 · 2025: 2 · 2024: 4 · 2023: 3 · 2022: 3 · 2021: 15 · 2020: 17 · 2019: 7
FWCI
4.85
Type
journal article
Language
en
Open access
closed
Locations
IEEE/ACM Transactions on Audio Speech and Language Processing (publishedVersion)
Funders
  • Ministry of Education, Singapore AcRF Tier1 NUS Start-up (FY2016)
  • SINGA Scholarship under A*STAR Graduate Academy
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
  • Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
Keywords
voice conversion, group sparse representation, spectrum conversion, phonetic posteriorgrams, phonetic dictionary, fundamental frequency, energy contour, limited training data

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Group Sparse Representation With WaveNet Vocoder Adaptation for Spectrum and Prosody Conversion. https://app.cochat.ai/papers/10.1109/taslp.2019.2910637
The paper
Sisman, B., Zhang, M., & Li, H. (2019). Group Sparse Representation With WaveNet Vocoder Adaptation for Spectrum and Prosody Conversion. IEEE/ACM Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/taslp.2019.2910637

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.