Adaspeech 2: Adaptive Text to Speech with Untranscribed Data
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Text to speech (TTS) is widely used to synthesize personal voice for a target speaker, where a well-trained source TTS model is fine-tuned with few paired adaptation data (speech and its transcripts) on this target speaker. However, in many scenarios, only untranscribed speech data is available for adaptation, which brings challenges to the previous TTS adaptation pipelines (e.g., AdaSpeech). In this paper, we develop AdaSpeech 2, an adaptive TTS system that only leverages untranscribed speech data for adaptation. Specifically, we introduce a mel-spectrogram encoder to a well-trained TTS model to conduct speech reconstruction, and at the same time constrain the output sequence of the mel-spectrogram encoder to be close to that of the original phoneme encoder. In adaptation, we use untranscribed speech data for speech reconstruction and only fine-tune the TTS decoder. AdaSpeech 2 has two advantages: 1) Pluggable: our system can be easily applied to existing trained TTS models without re-training. 2) Effective: our system achieves on-par voice quality with the transcribed TTS adaptation (e.g., AdaSpeech) with the same amount of untranscribed data, and achieves better voice quality than previous untranscribed adaptation methods1.
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
Tacotron: 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 1×
“TTS adaptation pipeline [1, 2, 3, 4, 5, 6, 7, 8] usually finetunes a well-trained multi-speaker TTS model [9, 10] (source model) with few adaptation data, and achieves good similarity with ground-truth human voice and high voice quality.”
BackgroundMelGAN: generative adversarial networks for conditional waveform synthesis
Kumar, K., Kumar, R., de Boissiere, T., Gestin, L., Teoh, W. Z., Sotelo, J., de Brebisson, A., Bengio, Y., & Courville, A. (2019) · arXiv · doi:10.48550/arxiv.1910.06711 · Cited by 722 · cited 1×
“We compare our proposed AdaSpeech 2 with other settings, which include: 1) GT, the ground-truth recordings; 2) GT mel + Vocoder, using ground-truth mel-spectrogram to synthesize waveform with MelGAN vocoder [20]; 3) a jointtraining method; 4) a PPG-based method; 5) AdaSpeech [8].”
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 2×
“Most previous works [1, 3, 4, 8] on TTS adaptation require paired data (speech and its transcripts), such as AdaSpeech [8].”
BackgroundZero-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 · cited 1×
“TTS adaptation pipeline [1, 2, 3, 4, 5, 6, 7, 8] usually finetunes a well-trained multi-speaker TTS model [9, 10] (source model) with few adaptation data, and achieves good similarity with ground-truth human voice and high voice quality.”
BackgroundMultiSpeech: Multi-Speaker Text to Speech with Transformer
Chen, M., Tan, X., Ren, Y., Xu, J., Sun, H., Zhao, S., & Qin, T. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-3139 · Cited by 92
Self-citationLibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
Zen, H., Dang, V., Clark, R., Zhang, Y., Weiss, R. J., Jia, Y., Chen, Z., & Wu, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.02882 · Cited by 23
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
“Tacotron 1/2 [72, 73] Ph→MelS NAR / Hybrid/Self-Att/CNN MelNet [361] Ch→MelS AR / RNN DeepVoice [8] Ch/Ph→MelS AR / CNN DeepVoice 2 [84] Ch/Ph→MelS AR / CNN DeepVoice 3 [264] Ch/Ph→MelS AR Seq2Seq CNN ParaNet [262] Ph→MelS NAR Seq2Seq CNN DCTTS [326] Ch→MelS AR Seq2Seq CNN SpeedySpeech [355] Ph→MelS NAR / CNN TalkNet…”
BackgroundInfluentialSelf-citationKhanjani, Z., Watson, G., & Janeja, V. P. (2023) · Frontiers in Big Data · doi:10.3389/fdata.2022.1001063 · Cited by 121
Adaptive Text to Speech for Spontaneous Style
Yan, Y., Tan, X., Li, B., Zhang, G., Qin, T., Zhao, S., Shen, Y., Zhang, W.-Q., & Liu, T.-Y. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-584 · Cited by 23
Self-citationWani, T. M., Qadri, S. A. A., Wani, F. A., & Amerini, I. (2024) · Foundations and Trends® in Privacy and Security · doi:10.1561/3300000048 · Cited by 16
Metadata
- Authors
- Yan, Y., Tan, X., Li, B., Qin, T., Zhao, S., Shen, Y., & Liu, T.-Y.
- Venue
- ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2021-06-06
- Pages
- 6613-6617
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W3161109662
- Cited by
- 45
- References
- 6
- FWCI
- 4.20
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Adaspeech 2: Adaptive Text to Speech with Untranscribed Data. https://app.cochat.ai/papers/10.1109/icassp39728.2021.9414872
- The paper
- Yan, Y., Tan, X., Li, B., Qin, T., Zhao, S., Shen, Y., & Liu, T.-Y. (2021). Adaspeech 2: Adaptive Text to Speech with Untranscribed Data. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp39728.2021.9414872
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.