WaveNet Vocoder with Limited Training Data for Voice Conversion
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
This paper investigates the approaches of building WaveNet vocoders with limited training data for voice conversion (VC). Current VC systems using statistical acoustic models always suffer from the quality degradation of converted speech. One of the major causes is the use of hand-crafted vocoders for wave-form generation. Recently, with the emergence of WaveNet for waveform modeling, speaker-dependent WaveNet vocoders have been proposed and they can reconstruct speech with better quality than conventional vocoders, such as STRAIGHT. Because training a WaveNet vocoder in the speaker-dependent way requires a relatively large training dataset, it remains a challenge to build a high-quality WaveNet vocoder for VC tasks when the training data of target speakers is limited. In this paper, we propose to build WaveNet vocoders by combining the initialization using a multi-speaker corpus and the adaptation using a small amount of target data, and evaluate this proposed method on the Voice Conversion Challenge (VCC) 2018 dataset which contains approximately 5 minute recordings for each target speaker. Experimental results show that the WaveNet vocoders built using our proposed method outperform conventional STRAIGHT vocoder. Furthermore, our system achieves an average naturalness MOS of 4.13 in VCC 2018, which is the highest among all submitted systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
Lorenzo-Trueba, J., Yamagishi, J., Toda, T., Saito, D., Villavicencio, F., Kinnunen, T., & Ling, Z. (2018) · The Speaker and Language Recognition Workshop (Odyssey 2018) · doi:10.21437/odyssey.2018-28 · Cited by 305
Self-citation
Cited by
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Wang, X., Yamagishi, J., Todisco, M., Delgado, H., Nautsch, A., Evans, N., Sahidullah, M., Vestman, V., Kinnunen, T., Lee, K. A., et al. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101114 · Cited by 505
“These WaveNet vocoders (μ-law companding and 10-bit quantization) were trained by pre-training them using an in-house multi-speaker corpus and fine-tuning it using the speech of target speakers [38].”
MethodSelf-citationAn Overview of Voice Conversion and Its Challenges: From Statistical Modeling to Deep Learning
Sisman, B., Yamagishi, J., King, S., & Li, H. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3038524 · Cited by 357
Voice Conversion Challenge 2020 –- Intra-lingual semi-parallel and cross-lingual voice conversion –-
Yi, Z., Huang, W.-C., Tian, X., Yamagishi, J., Das, R. K., Kinnunen, T., Ling, Z.-H., & Toda, T. (2020) · Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020 · doi:10.21437/vcc_bc.2020-14 · Cited by 126
Self-citationDeepfake Speech Detection: A Spectrogram Analysis
Firc, A., Malinka, K., & Hanáček, P. (2024) · Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing · doi:10.1145/3605098.3635911 · Cited by 16
“TTS and VC technologies are used, and some synthesis technology includes Variational Autoencoders [14, 43], Gaussian mixture models [25] or LSTM-RNN models [24, 42].”
Method
Metadata
- Authors
- Liu, L.-J., Ling, Z.-H., Jiang, Y., Zhou, M., & Dai, L.-R.
- Venue
- Interspeech 2018
- Publisher
- ISCA
- Published
- 2018-09-02
- Pages
- 1983-1987
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2889329491
- Cited by
- 124
- References
- 1
- FWCI
- 9.88
- Type
- conference paper
- Language
- en
- Open access
- closed
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
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.