Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach, which utilizes text supervision during training. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. During the training stage, an encoder-decoder-based hybrid connectionist-temporal-classification-attention (CTC-attention) phoneme recognizer is trained, whose encoder has a bottle-neck layer. A BNE is obtained from the phoneme recognizer and is utilized to extract speaker-independent, dense and rich spoken content representations from spectral features. Then a multi-speaker location-relative attention based seq2seq synthesis model is trained to reconstruct spectral features from the bottle-neck features, conditioning on speaker representations for speaker identity control in the generated speech. To mitigate the difficulties of using seq2seq models to align long sequences, we down-sample the input spectral feature along the temporal dimension and equip the synthesis model with a discretized mixture of logistic (MoL) attention mechanism. Since the phoneme recognizer is trained with large speech recognition data corpus, the proposed approach can conduct any-to-many voice conversion. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity. Ablation studies are conducted to confirm the effectiveness of feature selection and model design strategies in the proposed approach. The proposed VC approach can readily be extended to support any-to-any VC (also known as one/few-shot VC), and achieve high performance according to objective and subjective evaluations.
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
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Graves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
Generating Sequences With Recurrent Neural Networks
Graves, A. (2013) · arXiv · doi:10.48550/arxiv.1308.0850 · Cited by 2,894
VoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256
VoxCeleb: A Large-Scale Speaker Identification Dataset
Nagrani, A., Chung, J. S., & Zisserman, A. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-950 · Cited by 2,210 · cited 1×
“For any-to-any voice conversion, we use LibriSpeech (trainother-500), VoxCeleb1 [41] and VoxCeleb2 [42] datasets to train the speaker encoder introduced in Section III-C and Seciton IVD.”
MethodTacotron: towards end-to-end speech synthesis
Wang, Y., Skerry-Ryan, R. J., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Bengio, S., et al. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1452 · Cited by 1,746 · cited 2×
“A CBHG encoder [34] is adopted to transform phoneme”
MethodSalimans, T., Karpathy, A., Chen, X., & Kingma, D. P. (2017) · arXiv · doi:10.48550/arxiv.1701.05517 · Cited by 584 · cited 2×
“Inspired by [25], we incorporate a discretized mixture of logsitics (MoL) distribution [26] to model the attention weights in each decoding step in the BNESeq2seqMoL approach.”
Method“StarGAN-VC: non-parallel many-to-many voice conversion using star generative adversarial networks,”
Kameoka, H., Kaneko, T., Tanaka, K., & Hojo, N. (2018) · 2018 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639535 · Cited by 371
CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks
Kaneko, T., & Kameoka, H. (2018) · 2018 26th European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2018.8553236 · Cited by 358
AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
Qian, K., Zhang, Y., Chang, S., Yang, X., & Hasegawa-Johnson, M. (2019) · arXiv · doi:10.48550/arxiv.1905.05879 · Cited by 336
Cited by
A review of deep learning techniques for speech processing
Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., & Poria, S. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101869 · Cited by 389
Freevc: Towards High-Quality Text-Free One-Shot Voice Conversion
Li, J., Tu, W., & Xiao, L. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10095191 · Cited by 129
“…are selected to be compared with the proposed method: (1) VQMIVC [27], a text-free model that uses non-pretrained speaker encoder; (2) BNE-PPG-VC [6], a text-based model that uses pretrained speaker encoder; (3) YourTTS [28], a text-based model that extends VITS to one-shot setting by…”
BackgroundMethodInfluentialDomain Generalization via Aggregation and Separation for Audio Deepfake Detection
Xie, Y., Cheng, H., Wang, Y., & Ye, L. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3324724 · Cited by 59
Metadata
- Authors
- Liu, S., Cao, Y., Wang, D., Wu, X., Liu, X., & Meng, H.
- Venue
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Published
- 2021
- Volume
- 29
- Pages
- 1717-1728
- ISSN
- 2329-9290 (ISSN-L)
- 2329-9304
- OpenAlex
- W3083423753
- Cited by
- 83
- References
- 14
- FWCI
- 4.59
- Type
- journal article
- Language
- en
- Open access
- green
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: Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling. https://app.cochat.ai/papers/10.1109/taslp.2021.3076867
- The paper
- Liu, S., Cao, Y., Wang, D., Wu, X., Liu, X., & Meng, H. (2021). Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling. IEEE/ACM Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/taslp.2021.3076867
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.