CoChat

Statistical parametric speech synthesis using deep neural networks

Zen, Heiga, Senior, Andrew, Schuster, Mike · 2013 · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Cited by 809

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Abstract

Conventional approaches to statistical parametric speech synthesis typically use decision tree-clustered context-dependent hidden Markov models (HMMs) to represent probability densities of speech parameters given texts. Speech parameters are generated from the probability densities to maximize their output probabilities, then a speech waveform is reconstructed from the generated parameters. This approach is reasonably effective but has a couple of limitations, e.g. decision trees are inefficient to model complex context dependencies. This paper examines an alternative scheme that is based on a deep neural network (DNN). The relationship between input texts and their acoustic realizations is modeled by a DNN. The use of the DNN can address some limitations of the conventional approach. Experimental results show that the DNN-based systems outperformed the HMM-based systems with similar numbers of parameters.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icassp.2013.6639215

Cites

27 of 27 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 17

  1. 10.1016/j.specom.2011.03.003 · doi:10.1016/j.specom.2011.03.003
  2. 10.1109/ICASSP.2011.5947369 · doi:10.1109/icassp.2011.5947369
  3. tokuda, 2002, Multi-space probability distribution HMM, IEICE Trans Inf Syst, e85 d, 455
  4. 10.1109/ICASSP.1999.758133 · doi:10.1109/icassp.1999.758133
  5. 10.1109/ICASSP.2006.1660231 · doi:10.1109/icassp.2006.1660231
  6. odell, 1995, The use of context in large vocabulary speech recognition
  7. shinoda, 1997, Acoustic modeling based on the MDL criterion for speech recognition, Proc EUROSPEECH, 99, 10.21437/Eurospeech.1997-52 · doi:10.21437/eurospeech.1997-52
  8. 10.1109/TASL.2010.2076805 · doi:10.1109/tasl.2010.2076805
  9. qian, 2008, Generating natural F0 trajectory with additive trees, Proc INTERSPEECH, 2126, 10.21437/Interspeech.2008-551 · doi:10.21437/interspeech.2008-551
  10. nankaku, 2008, Acoustic modeling with contextual additive structure for HMM-based speech recognition, Proc ICASSP, 4469
  11. saino, 2008, A Clustering Technique for Factor Analysis-based Eigenvoice Models
  12. 10.1109/ICASSP.2010.5495690 · doi:10.1109/icassp.2010.5495690
  13. 10.1109/ICASSP.2001.941037 · doi:10.1109/icassp.2001.941037
  14. morioka, 2004, Miniaturization of HMM-based speech synthesis, Procs ASJ Autumn Meeting, 325
  15. 10.1093/ietisy/e90-d.9.1406 · doi:10.1093/ietisy/e90-d.9.1406
  16. shichiri, 2002, Eigenvoices for HMM-based speech synthesis, Proc ICSLP, 1269
  17. gutkin, 2010, Quantized HMMs for low footprint text-to-speech synthesis, Proc INTERSPEECH, 837, 10.21437/Interspeech.2010-186 · doi:10.21437/interspeech.2010-186

Cited by

See all 809

Metadata

Authors
Zen, H., Senior, A., & Schuster, M.
Venue
2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Publisher
IEEE
Published
2013-05
Pages
7962-7966
ISSN
1520-6149 (ISSN-L)
OpenAlex
W2102003408
Cited by
809
References
27
FWCI
39.24
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.