Neural Text-to-Speech Adaptation from Low Quality Public Recordings
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Neural Text-to-Speech (TTS) synthesis is able to generate high-quality speech with natural prosody. However, these systems typically require a large amount of data, preferably recorded in a clean and noise-free environment. We focus on creating target voices from low quality public recordings and our findings show that even with a large amount of data from a specific speaker, it is challenging to train a speaker-dependent neural TTS model. In order to improve the voice quality, while simultaneously reducing the amount of data required, we introduce meta-learning to adapt the neural TTS front-end. We propose three approaches for multi-speaker systems: (1) a lookup-table-based system, (2) a speaker representation derived from the Personalized Hey Siri (PHS) system, and (3) a system with no speaker encoder. Re-sults show that: i) By using a significantly smaller number of target voice recordings, the proposed system based on embed-dings trained from the PHS system can generate comparable quality and speaker similarity to the speaker-dependent model trained solely on the target voice. ii) Applying meta-learning to Tacotron can effectively learn a representation of an unseen speaker. iii) For low quality public recordings, the adaptation based on the multi-speaker corpus can generate a cleaner target voice in comparison with the speaker-dependent model.
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
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“The parameters of the speaker encoder are optimized via a curriculum learning procedure [30] to improve robustness under various acoustic conditions and text variability.”
MethodTransfer learning from speaker verification to multispeaker text-to-speech synthesis
Jia, Y., Zhang, Y., Weiss, R. J., Wang, Q., Shen, J., Ren, F., Chen, Z., Nguyen, P., Pang, R., Moreno, I. L., et al. (2018) · arXiv · doi:10.48550/arxiv.1806.04558 · Cited by 519 · cited 7×
“[16] has shown the effectiveness of decoupling the speaker encoder from speech synthesis by training a speaker verification model.”
BackgroundMethodInfluentialMean opinion score (MOS) revisited: Methods and applications, limitations and alternatives
Streijl, R. C., Winkler, S., & Hands, D. S. (2016) · Multimedia Systems · doi:10.1007/s00530-014-0446-1 · Cited by 506 · cited 1×
“Synthesized voices are evaluated from three aspects: 1) the speech naturalness Mean Opinion Score (MOS) (from 1 to 5) [34] 2) speaker similarity MOS (from 1 to 5) compared to the target speaker voice 3) Signal Noise Ratio (SNR).”
Background
Cited by
A survey on neural speech synthesis
Tan, X., Qin, T., Soong, F., & Liu, T.-Y. (2021) · arXiv · doi:10.48550/arxiv.2106.15561 · Cited by 216
“[119] propose to mine this kind of data and develop sophisticated techniques to train a TTS model.”
MethodZero-Shot Multi-Speaker Text-To-Speech with State-Of-The-Art Neural Speaker Embeddings
Cooper, E., Lai, C.-I., Yasuda, Y., Fang, F., Wang, X., Chen, N., & Yamagishi, J. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054535 · Cited by 164
“Prior studies have focused on training a speaker encoder network jointly with the TTS model [6, 8, 9] or the neural vocoder [10]; others have explored the use of speaker embeddings in combination with fine-tuning the TTS model [10, 11, 12].”
MethodSaka, A. B., Oyedele, L. O., Akanbi, L. A., Ganiyu, S. A., Chan, D. W. M., & Bello, S. A. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2022.101869 · Cited by 161
Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding
Choi, S., Han, S., Kim, D., & Ha, S. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-2096 · Cited by 56
Metadata
- Authors
- Hu, Q., Marchi, E., Winarsky, D., Stylianou, Y., Naik, D., & Kajarekar, S.
- Venue
- 10th ISCA Workshop on Speech Synthesis (SSW 10)
- Publisher
- ISCA
- Published
- 2019-09-20
- Pages
- 24-28
- OpenAlex
- W2972440097
- Cited by
- 31
- References
- 3
- FWCI
- 2.10
- 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.