The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech
Abstract
The quality of text-to-speech (TTS) voices built from noisy speech is compromised. Enhancing the speech data before training has been shown to improve quality but voices built with clean speech are still preferred. In this paper we investigate two different approaches for speech enhancement to train TTS systems. In both approaches we train a recursive neural network (RNN) to map acoustic features extracted from noisy speech to features describing clean speech. The enhanced data is then used to train the TTS acoustic model. In one approach we use the features conventionally employed to train TTS acoustic models, i.e Mel cepstral (MCEP) coefficients, aperiodicity values and fundamental frequency (F0). In the other approach, following conventional speech enhancement methods, we train an RNN using only the MCEP coefficients extracted from the magnitude spectrum. The enhanced MCEP features and the phase extracted from noisy speech are combined to reconstruct the waveform which is then used to extract acoustic features to train the TTS system. We show that the second approach results in larger MCEP distortion but smaller F0 errors. Subjective evaluation shows that synthetic voices trained with data enhanced with this method were rated higher and with similar to scores to voices trained with clean speech.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893
Learning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542
Learning to forget: Continual prediction with LSTM
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000) · Neural Computation · doi:10.1162/089976600300015015 · Cited by 4,823
Kawahara, H., Masuda-Katsuse, I., & de Cheveigné, A. (1999) · Speech Communication · doi:10.1016/s0167-6393(98)00085-5 · Cited by 1,831
A Regression Approach to Speech Enhancement Based on Deep Neural Networks
Xu, Y., Du, J., Dai, L.-R., & Lee, C.-H. (2015) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2364452 · Cited by 1,366
Statistical parametric speech synthesis
Zen, H., Tokuda, K., & Black, A. W. (2009) · Speech Communication · doi:10.1016/j.specom.2009.04.004 · Cited by 1,195
Speech parameter generation algorithms for HMM-based speech synthesis
Tokuda, K., Yoshimura, T., Masuko, T., Kobayashi, T., & Kitamura, T. (2002) · 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100) · doi:10.1109/icassp.2000.861820 · Cited by 999
Sak, H., Senior, A., & Beaufays, F. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1402.1128 · Cited by 838
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
Weninger, F., Erdogan, H., Watanabe, S., Vincent, E., Le Roux, J., Hershey, J. R., & Schuller, B. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-22482-4_11 · Cited by 602
TTS synthesis with bidirectional LSTM based recurrent neural networks
Fan, Y., Qian, Y., Xie, F.-L., & Soong, F. K. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-443 · Cited by 426
Veaux, C., Yamagishi, J., & King, S. (2013) · 2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) · doi:10.1109/icsda.2013.6709856 · Cited by 398
Self-citationA Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis
TODA, T., & TOKUDA, K. (2007) · IEICE Transactions on Information and Systems · doi:10.1093/ietisy/e90-d.5.816 · Cited by 358
Thiemann, J., Ito, N., & Vincent, E. (2013) · The Journal of the Acoustical Society of America · doi:10.1121/1.4806631 · Cited by 346
Yamagishi, J., Kobayashi, T., Nakano, Y., Ogata, K., & Isogai, J. (2009) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2008.2006647 · Cited by 324
Self-citationDiscriminatively trained recurrent neural networks for single-channel speech separation
Weninger, F., Hershey, J. R., Le Roux, J., & Schuller, B. (2014) · 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP) · doi:10.1109/globalsip.2014.7032183 · Cited by 283
Zen, H., & Sak, H. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178816 · Cited by 262
Subjective Comparison of Speech Enhancement Algorithms
Hu, Y., & Loizou, P. C. (2006) · 2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings · doi:10.1109/icassp.2006.1659980 · Cited by 230
An RNN-based prosodic information synthesizer for Mandarin text-to-speech
Chen, S.-H., Hwang, S.-H., & Wang, Y.-R. (1998) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.668817 · Cited by 162
Introducing CURRENNT: the Munich open-source CUDA recurrent neural network toolkit
Weninger, F. J., Bergmann, J. M., & Schuller, B. W. (2015) · Spiral (Imperial College London) · Cited by 154
Valentini-Botinhao, C., Wang, X., Takaki, S., & Yamagishi, J. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-159 · Cited by 132
Self-citationA deep neural network for time-domain signal reconstruction
Wang, Y., & Wang, D. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178800 · Cited by 100
Yamagishi, J., Veaux, C., King, S., & Renals, S. J. (2012) · Nippon Onkyo Gakkaishi/Acoustical science and technology/Nihon Onkyo Gakkaishi · doi:10.1250/ast.33.1 · Cited by 93
Self-citationFernandez, R., Rendel, A., Ramabhadran, B., & Hoory, R. (2014) · Interspeech (USB) · doi:10.21437/interspeech.2014-445 · Cited by 76
Robustness of HMM-based speech synthesis
Yamagishi, J., Ling, Z.-H., & King, S. (2008) · Interspeech (USB) · doi:10.21437/interspeech.2008-171 · Cited by 44
Self-citationAchanta, S., Godambe, T., & Gangashetty, S. V. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-266 · Cited by 22
Noise in HMM-Based Speech Synthesis Adaptation: Analysis, Evaluation Methods and Experiments
Karhila, R., Remes, U., & Kurimo, M. (2014) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2013.2278492 · Cited by 16
Analysis of speaker clustering strategies for HMM-based speech synthesis
Dall, R., Veaux, C., Yamagishi, J., & King, S. (2012) · Interspeech (USB) · doi:10.21437/interspeech.2012-295 · Cited by 14
Self-citation
Cited by
SEGAN: Speech Enhancement Generative Adversarial Network
Pascual, S., Bonafonte, A., & Serrà, J. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1428 · Cited by 1,297
A Wavenet for Speech Denoising
Rethage, D., Pons, J., & Serra, X. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8462417 · Cited by 457
PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network
Yin, D., Luo, C., Xiong, Z., & Zeng, W. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6489 · Cited by 323
Real-Time Speech Enhancement Using Equilibriated RNN
Takeuchi, D., Yatabe, K., Koizumi, Y., Oikawa, Y., & Harada, N. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054597 · Cited by 48
Metadata
- Authors
- Valentini-Botinhao, C., Wang, X., Takaki, S., & Yamagishi, J.
- Venue
- 9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)
- Publisher
- ISCA
- Published
- 2016-09-13
- Pages
- 146-152
- OpenAlex
- W2603567530
- Cited by
- 463
- References
- 28
- FWCI
- 5.99
- 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.