Hidden Markov Models in Speech Synthesis: Difference between revisions

From MSc Voice Technology
Jump to navigation Jump to search
VisualWikitext
No edit summary
No edit summary
Line 85: Line 85:
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.


== Future research ==
== Future Research ==
HMM-based speech synthesis has shown promise in generating speech with diverse speaking styles and demands less storage (Drugman et al., 2009)<ref>Drugman, T, Wilfart G, Dutoit T (2009) A deterministic plus stochastic model of the residual signal for improved parametric speech synthesis.</ref>. This has led to the emergence of several applications, notably: a) personalized speech-to-speech translation systems<ref>Y. Qian, H. Liang, and F. K. Soong, “A cross-language state sharing and mapping approach to bilingual (Mandarin – English) TTS,” IEEE Trans. Audio Speech Lang. Process., vol. 17, no. 6, pp. 1231–1239, Aug. 2009.</ref><ref>Y.-J. Wu, S. King, and K. Tokuda, “Cross-language speaker adaptation for HMM-based speech synthesis,” in Proc. ISCSLP, 2008, pp. 9–12.</ref><ref>K. Oura, J. Yamagishi, M. Wester, S. King, and K. Tokuda, “Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping,” Speech Commun., vol. 54, no. 6, pp. 703–714, 2012.</ref> and b) personalized speech synthesizers for individuals with vocal disabilities <ref>J. Yamagishi, C. Veaux, S. King, and S. Renals, “Speech synthesis technologies for individuals with vocal disabilities: voice banking and reconstruction,” in Acoustical Science & Technology, 2012, vol. 33, pp. 1–5.</ref> and HTS is also widely applied in [[Commerical TTS - Google, Amazon, Apple and Microsoft (2010s)]].  
HMM-based speech synthesis has shown promise in generating speech with diverse speaking styles and demands less storage (Drugman et al., 2009)<ref>Drugman, T, Wilfart G, Dutoit T (2009) A deterministic plus stochastic model of the residual signal for improved parametric speech synthesis.</ref>. This has led to the emergence of several applications, notably: a) personalized speech-to-speech translation systems<ref>Y. Qian, H. Liang, and F. K. Soong, “A cross-language state sharing and mapping approach to bilingual (Mandarin – English) TTS,” IEEE Trans. Audio Speech Lang. Process., vol. 17, no. 6, pp. 1231–1239, Aug. 2009.</ref><ref>Y.-J. Wu, S. King, and K. Tokuda, “Cross-language speaker adaptation for HMM-based speech synthesis,” in Proc. ISCSLP, 2008, pp. 9–12.</ref><ref>K. Oura, J. Yamagishi, M. Wester, S. King, and K. Tokuda, “Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping,” Speech Commun., vol. 54, no. 6, pp. 703–714, 2012.</ref> and b) personalized speech synthesizers for individuals with vocal disabilities <ref>J. Yamagishi, C. Veaux, S. King, and S. Renals, “Speech synthesis technologies for individuals with vocal disabilities: voice banking and reconstruction,” in Acoustical Science & Technology, 2012, vol. 33, pp. 1–5.</ref> and HTS is also widely applied in [[Commerical TTS - Google, Amazon, Apple and Microsoft (2010s)]].  


Line 93: Line 93:


== Members ==
== Members ==
Jingwen Shi
Youyang Cai --- [Introduction]


Yining Lei
Weixi Lai --- [Historical Context]


Weixi Lai
Jingwen Shi --- [Key Innovations]


Youyang Cai
Siqi Zheng --- [Impact]


Siqi Zheng
Yining Lei --- [Future Research]
== References ==
== References ==
To insert a reference, type <nowiki><ref> and paste the source your exported from Zotero (or whatever reference manager you're using) in the pop up box which appears. Make sure links in citations are clickable using proper formatting. Once you do this, a footnote will appear.</nowiki> and a reference comes at the end automatically. Please use this method to cite for Wiki articles only, not for your thesis.
To insert a reference, type <nowiki><ref> and paste the source your exported from Zotero (or whatever reference manager you're using) in the pop up box which appears. Make sure links in citations are clickable using proper formatting. Once you do this, a footnote will appear.</nowiki> and a reference comes at the end automatically. Please use this method to cite for Wiki articles only, not for your thesis.

Revision as of 22:37, 14 October 2023

Introduction

Hidden Markov Model (HMM)-based speech synthesis is a remarkably effective technique in synthesizing speech. The most attractive part of HTS system is that speaker identities, speaking styles, or emotions can easily be modified by transforming HMM parameters using various techniques such as adaptation, interpolation, Eigen voice, Or multiple Regression.

In the realm of Text-to-speech (TTS) synthesis, the main goal is to transform input text into intelligible and natural sounding speech. The TTS components involves the two phases, the front end and the back end. The front end analyses the text, creates possible pronunciations for each word in the context with grapheme to phoneme conversion. The back end generates the speech waveform along with the prosody of the sentence to be spoken. The evaluation of TTS system is based on three critical attributes: accuracy, intelligibility, and naturalness.

The HTS system provides the frequency spectrum (Vocal tract), fundamental frequency (vocal source) and duration (Prosody) of speech, which are statistically generated by using HMM based on maximum likelihood criterion. HTS system is an open source tool which provides a research and development platform for statistical parametric speech synthesis. The HMM-based speech synthesis system (HTS) has been developed by the HTS working group as an extension of the HMM toolkit (HTK)[1].

Historical Context

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.

Key Innovations

The key innovations of Hidden Markov Model (HMM) in the field of speech synthesis primarily focus on several critical aspects:

High-Precision Model Design

Researchers continuously improve the structure and parameter estimation methods of Hidden Markov Model (HMM) to enhance its precision and accuracy in speech synthesis. This includes modeling improvements in states, transition probabilities, emission probabilities, and more. Key innovations in high-precision model design in the domain of speech synthesis with HMMs focus on enhancing the model's structure, parameter estimation methods, and integration with neural networks. These innovations play a crucial role in improving the accuracy, temporal modeling capabilities, and expressive power of HMMs, providing valuable insights and methods for high-precision model design in speech synthesis. These innovations make HMM models more adaptable and expressive in the field of speech synthesis, laying the foundation for achieving high-quality, natural speech synthesis.

Improved Model Structure

  1. Multi-layer HMMs: Introducing multi-layer HMMs to better represent the intricate structure of speech signals. [Young et al., 1994][2]
  2. Coupled HMMs: Coupling multiple HMM models to enhance the modeling of complex speech features. [Lee and Hon, 1989][3]

Parameter Estimation Methods

  1. Maximum Likelihood Estimation(MLE): Employing MLE to estimate parameters like state transition and emission probabilities, enhancing model fitting accuracy. [Rabiner and Juang, 1986][4]
  2. Baum-Welch Algorithm: Utilizing the Baum-Welch algorithm for iterative parameter estimation, maximizing the likelihood function of observed data. [Baum et al., 1970][5]

Integration with Neural Networks

  1. Combination of Deep Neural Network and HMM (DNN-HMM): Fusing deep neural networks with HMM to model the relationship between speech features and HMM states, enhancing the model's expression ability. [Hinton et al., 2012][6]
  2. Combination of Recurrent Neural Network and HMM (RNN-HMM): Integrating recurrent neural networks with HMM to model temporal information, further improving the time series modeling ability. [Graves et al., 2013][7]

Hybrid Model and State Aggregation

Introducing more complex mixture models or state aggregation methods to enhance the model's ability to model diverse speech features, making synthesized speech sound more natural. Key innovations in mixture models and state aggregation in the domain of speech synthesis with HMMs primarily focus on model structure design and parameter optimization. Mixture models and state aggregation help improve HMMs' ability to model complex speech features, resulting in more natural synthesized speech.

Hybrid Models

  1. Gaussian Mixture Models (GMMs): Frequently used to model HMM state output probability, enhancing the modeling ability for speech features. [Reynolds et al., 2000][8]
  2. Various Output Probability Distributions: Introduction of different distributions to more accurately describe the distribution of speech features, thereby improving the quality and naturalness of synthetic speech.

State Aggregation

  1. Tied-State Models: Aggregating states with similar characteristics and sharing state parameters to reduce model complexity and improve efficiency. [Bahl et al., 1986][9]
  2. State Merging of Sub-word Units: Merging states of different sub-word units to reduce model complexity and enhance modeling ability for diverse speech features. [Juang and Rabiner, 1991][10]

Time Series Model Optimization

Optimizing the model's temporal properties to better capture the temporal variations in speech signals, especially in terms of coherence and fluency between different phonemes. Key innovations in temporal model optimization in the domain of speech synthesis with HMMs primarily focus on improving the model's ability to model temporal properties, handle long sequences, and enhance the model's temporal prediction accuracy. These innovations have significantly advanced HMM models in temporal modeling, laying the foundation for achieving more natural and fluent speech synthesis.

Long-term Sequential Modeling

  1. Methods for Long-time Sequence Modeling: Addressing long-time sequence problems by introducing methods to capture long-time sequence features more accurately, enhancing the naturalness of synthetic speech. [Tjandra et al., 2017][11]
  2. Long-term Sequence Memory Mechanisms: Implementing long-term sequence memory mechanisms like gated recurrent units (GRU) or long-short-term memory networks (LSTM) to effectively capture long-term sequence information and improve timing modeling ability. [Chung et al., 2015][12]

Improved Accuracy of Time Series Prediction

  1. Enhanced Training Strategies: Utilizing enhanced training strategies, such as reinforcement learning, to optimize the prediction accuracy of the time series, resulting in more natural rhythm and fluency in synthetic speech. [Ping et al., 2018][13]
  2. Model Fusion: Fusing HMM with other models, such as neural networks, to achieve higher timing modeling accuracy and prediction ability, resulting in smoother and more natural synthetic speech. [Zen et al., 2009][14]

HMM Improvement Based on Neural Networks

Integrating neural networks with HMM, such as Deep Neural Network-HMM (DNN-HMM) and Recurrent Neural Network-HMM (RNN-HMM), to enhance the model's expressive power and efficiency. Significant innovations in improving HMMs based on neural networks in the field of speech synthesis focus on combining neural networks with HMMs to enhance the model's expressive power, accuracy, and naturalness. These innovations combining neural networks with HMMs result in models with stronger expressive capabilities, more accurate modeling, and more natural speech synthesis effects.

Integration of Deep Neural Network and HMM (DNN-HMM)

  1. DNN for Acoustic Modeling: Employing deep neural networks to model HMM state emission probability, replacing the traditional Gaussian mixture model (GMM), significantly enhancing the accuracy and naturalness of the speech synthesis system. [Hinton et al., 2012][6]
  2. DNN as a Front-end Feature Extractor: Utilizing DNN as a feature extractor and its output as the input feature of HMM to enhance feature representation. [Zeiler et al., 2013][15]

Integration of Recurrent Neural Network and HMM (RNN-HMM)

  1. RNN for Timing Modeling: Integrating recurrent neural networks (RNN) to model the timing of HMM, better capturing long-term information and improving fluency and naturalness of synthetic speech. [Graves et al., 2013][16]
  2. Long-term Sequence Modeling: Introducing long-term memory networks (LSTM) as a variant of RNN to address the problem of gradient vanishing in long-time series modeling and improve the time series modeling ability. [Hochreiter and Schmidhuber, 1997][17]

End-to-End Learning

Adopting an end-to-end learning approach, mapping input text directly to acoustic features, avoiding manually designed feature extraction steps, simplifying the system, and improving performance. Key innovations in end-to-end learning in the domain of speech synthesis with HMMs primarily focus on the direct mapping from input text to synthesized speech in end-to-end model design and training. This approach bypasses the cumbersome intermediate steps in traditional speech synthesis systems and directly maps text to corresponding acoustic features. These innovations have made end-to-end learning a significant research direction in the field of speech synthesis, greatly simplifying the system flow while improving the quality and naturalness of synthesized speech.

End-to-End Model Design

  1. Text-to-Speech End-to-End Model: Designing an integrated neural network model that takes text as input and outputs corresponding acoustic features, achieving direct mapping from text to acoustic features. [Wang et al., 2017][18]
  2. Self-Attention Mechanism: Introducing a self-attention mechanism to capture long-distance dependencies in input text, enhancing the model's ability to handle longer texts. [Shen et al., 2018][19]

Joint Training

  1. Joint Training of Text and Acoustic Features: Training an end-to-end model to jointly predict text and acoustic features for improved performance and more natural speech synthesis results. [Wang et al., 2017][18]
  2. Reinforcement Learning Optimization: Leveraging reinforcement learning to optimize the model, enabling it to generate acoustic feature sequences that align better with the fluency of natural speech. [Ping et al., 2017][20]

Emotion and Intonation Synthesis

Integrating emotion and intonation information into the HMM model to achieve more rich and vivid speech synthesis, allowing synthesized speech to convey a broader range of emotional nuances and expressions. Key innovations in emotion and intonation synthesis in the domain of speech synthesis with HMMs primarily focus on model structure, feature extraction, and the use of emotion-annotated data. These innovations aim to make synthesized speech more emotionally expressive and closer to natural speech. These innovations have significantly improved HMM models in emotion and intonation synthesis, providing important insights and methods for achieving more rich and natural speech synthesis.

Emotional Modeling

  1. Emotion-Driven HMM Model: Designing an emotion-driven HMM model that takes emotion tags as input features, enabling the model to adjust synthetic speech characteristics based on emotional information for emotional synthesis. [Mills et al., 2012][21]
  2. Modeling Emotion in a Multidimensional Space: Treating emotion as a multi-dimensional space and synthesizing different emotions by modeling speech feature distribution in this space. [Schuller et al., 2003][22]

Intonation Modeling

  1. Intonation Modeling Based on Prosodic Patterns: Introducing prosodic pattern modeling to simulate intonation by adjusting pitch and volume. [Hunt and Black, 1996][23]
  2. F0 Profile Modeling: Controlling intonation in speech synthesis by modeling the F0 (fundamental frequency) profile, representing pitch changes in sound. [Tóth and Bánhalmi, 2011][24]

Impact

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.

Future Research

HMM-based speech synthesis has shown promise in generating speech with diverse speaking styles and demands less storage (Drugman et al., 2009)[25]. This has led to the emergence of several applications, notably: a) personalized speech-to-speech translation systems[26][27][28] and b) personalized speech synthesizers for individuals with vocal disabilities [29] and HTS is also widely applied in Commerical TTS - Google, Amazon, Apple and Microsoft (2010s).

However, despite these advantages, HTS does possess a few limitations and requires improving. Primarily, enhancing the intelligibility of synthetic speech in noise remains a challenge. Researchers have pointed out that unmodified synthetic speech tends to experience a more pronounced reduction in intelligibility compared to unmodified natural speech in noisy environments [30]. Secondly, HMM-based synthesis faces constraints related to acoustic modeling accuracy. The statistical averaging process used in parametric methods generates smooth speech trajectories, resulting in muffled speech and sometimes incorrectly extracts pitch information[31].

Looking ahead, there are many directions for further research in the future. For the quality of the synthesized speech, Kawahara et al. proposed pitch-adaptive spectral analysis combined with a surface reconstruction method and an excitation method using instantaneous frequency calculation[32].Addressing F0 modeling, a statistical model of speech fundamental frequency contours has been proposed [33] based on the formulation of the discrete-time stochastic process version of the Fujisaki model [34]. On a different trajectory, focusing on speech synthesis using "Big data" [35], which includes ebooks, Internet radio, podcasts, etc., has shown potential. Training HMMs with automatic speech transcription that encompasses errors is one approach in this domain. Additionally, a framework for the analysis of emotion in texts for speech synthesis has been introduced [36], allowing the automatic translation of plain texts into appropriate speaking styles. Speech synthesis via physical simulation, particularly an MRI-based articulatory speech synthesis system, is another avenue being explored [37].

Members

Youyang Cai --- [Introduction]

Weixi Lai --- [Historical Context]

Jingwen Shi --- [Key Innovations]

Siqi Zheng --- [Impact]

Yining Lei --- [Future Research]

References

To insert a reference, type <ref> and paste the source your exported from Zotero (or whatever reference manager you're using) in the pop up box which appears. Make sure links in citations are clickable using proper formatting. Once you do this, a footnote will appear. and a reference comes at the end automatically. Please use this method to cite for Wiki articles only, not for your thesis.

  1. ↑ Kayte, S., Mundada, M., & Gujrathi, J. (2015). Hidden Markov model based speech synthesis: A review. International Journal of Computer Applications, 130(3), 35-39.
  2. ↑ Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., ... & Woodland, P. (1994). The HTK Book. Cambridge University Engineering Department.
  3. ↑ Lee, K.-F., & Hon, H.-W. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(11), 1641-1648.
  4. ↑ Rabiner, L. R., & Juang, B. H. (1986). An introduction to hidden Markov models. IEEE ASSP Magazine, 3(1), 4-16.
  5. ↑ - Baum, L. E., Petrie, T., Soules, G., & Weiss, N. (1970). A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. The annals of mathematical statistics, 41(1), 164-171.
  6. ↑ 6.0 6.1 Hinton, G. E., Deng, L., Yu, D., Dahl, G. E., Mohamed, A. R., Jaitly, N., ... & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82-97.
  7. ↑ Graves, A., Mohamed, A. R., Hinton, G., (2013). Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (ICASSP), 2013 IEEE international conference (pp. 6645-6649).
  8. ↑ Reynolds, D. A., Rose, R. C., & Quatieri, T. F. (2000). Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Transactions on Speech and Audio Processing, 8(2), 128-142.
  9. ↑ Bahl, L. R., Jelinek, F., & Mercer, R. L. (1986). A maximum likelihood approach to continuous speech recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, (5), 179-190.
  10. ↑ Juang, B. H., & Rabiner, L. R. (1991). Hidden Markov models for speech recognition. Technometrics, 33(3), 251-272.
  11. ↑ Tjandra, A., Cohn, T., Schuster, M., & Schröder, S. (2017). Listening while speaking: Speech recognition during speech production is modulated by visually perceived speech rate. PloS one, 12(3), e0173612.
  12. ↑ Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2015). Gated feedback recurrent neural networks. In Proceedings of the 32nd International Conference on International Conference on Machine Learning (pp. 2067-2075).
  13. ↑ Ping, W., Peng, B., & Yang, X. (2018). Deep voice 3: 2000-speaker neural text-to-speech. In Advances in Neural Information Processing Systems (pp. 4967-4977).
  14. ↑ Zen, H., Tokuda, K., Masuko, T., Kobayashi, T., & Kitamura, T. (2009). HMM-based speech synthesis integrated with speaker adaptation and its evaluation. IEEE Transactions on Audio, Speech, and Language Processing, 17(2), 363-376.
  15. ↑ Zeiler, M. D., Krishnan, D., Taylor, G. W., Fergus, R. (2013). Deconvolutional networks. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on (pp. 2528-2535).
  16. ↑ Graves, A., Mohamed, A. R., Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (ICASSP), 2013 IEEE international conference (pp. 6645-6649).
  17. ↑ Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
  18. ↑ 18.0 18.1 Wang, Y., Skerry-Ryan, R. J., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., ... & Auli, M. (2017). Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135.
  19. ↑ Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., ... & Wu, Y. (2018). Natural TTS synthesis by conditioning WaveNet on Mel spectrogram predictions. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4779-4783).
  20. ↑ Ping, W., Peng, B., & Yang, X. (2017). Deep Voice 3: 2000-speaker neural text-to-speech. In Advances in Neural Information Processing Systems (pp. 4967-4977).
  21. ↑ Mills, G., & Schuller, B. W. (2012). HMM-based synthesis of emotional speech with multi-formant filter representation. In Proceedings of the 4th International Workshop on Emotion Corpora and Recognition (pp. 9-14).
  22. ↑ Schuller, B., Batliner, A., Seppi, D., Steidl, S., Vogt, T., Wagner, J., ... & Devillers, L. (2003). The relevance of feature type for the automatic classification of emotional user states: Low level descriptors and functionals. In European Conference on Speech Communication and Technology.
  23. ↑ Hunt, A., & Black, A. (1996). Unit selection in a concatenative speech synthesis system using a large speech database. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 373-376).
  24. ↑ Tóth, L., & Bánhalmi, A. (2011). HMM-based synthesis of F0 contours for TTS. In Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH) (pp. 749-752).
  25. ↑ Drugman, T, Wilfart G, Dutoit T (2009) A deterministic plus stochastic model of the residual signal for improved parametric speech synthesis.
  26. ↑ Y. Qian, H. Liang, and F. K. Soong, “A cross-language state sharing and mapping approach to bilingual (Mandarin – English) TTS,” IEEE Trans. Audio Speech Lang. Process., vol. 17, no. 6, pp. 1231–1239, Aug. 2009.
  27. ↑ Y.-J. Wu, S. King, and K. Tokuda, “Cross-language speaker adaptation for HMM-based speech synthesis,” in Proc. ISCSLP, 2008, pp. 9–12.
  28. ↑ K. Oura, J. Yamagishi, M. Wester, S. King, and K. Tokuda, “Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping,” Speech Commun., vol. 54, no. 6, pp. 703–714, 2012.
  29. ↑ J. Yamagishi, C. Veaux, S. King, and S. Renals, “Speech synthesis technologies for individuals with vocal disabilities: voice banking and reconstruction,” in Acoustical Science & Technology, 2012, vol. 33, pp. 1–5.
  30. ↑ S. King and V. Karaiskos, “The Blizzard Challenge 2010,” in Proc. Blizzard Challenge Workshop, Kyoto, Japan, Sep. 2010.
  31. ↑ Zen H, Tokuda K, Black AW (2009) Statistical parametric speech synthesis. Speech Commun 51(11):10391064.
  32. ↑ H. Kawahara, I. Masuda-Katsuse, and A. Cheveigne, “Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based f0 extraction: possible role of a repetitive structure in sounds,” Speech Commun., vol. 27, pp. 187–207, 1999.
  33. ↑ H. Kameoka, J. Le Roux, and Y. Ohishi, “A statistical model of speech F0 contours,” in Proc. SAPA, 2010, pp. 43–48.
  34. ↑ H. Fujisaki and K. Hirose, “Analysis of voice fundamental frequency contours for declarative sentences of Japanese,” J. Acoust. Soc. Jpn. (E), vol. 5, no. 4, pp. 233–242, 1984.
  35. ↑ J. Ni and H. Kawai, “On the effects of transcript errors across dataset sizes on hmm-based voices,” in Proc. the Autumn Meeting of ASJ, 2011, pp. 339–342.
  36. ↑ J. R. Bellegarda, “A data-driven affective analysis framework toward naturally expressive speech synthesis,” IEEE Trans. Audio Speech Lang. Process., vol. 19, no. 5, pp. 1113–1122, 2011.
  37. ↑ T. Kitamura, H. Takemoto, P. Mokhtari, and T. Hirai, “MRI-based time-domain speech synthesis system,” in Proc. ASA/ASJ joint meeting, 2006.
Retrieved from "http://wiki.voice-technology.nl/index.php?title=Hidden_Markov_Models_in_Speech_Synthesis&oldid=1234"