- 著者
- Kazuhiro NAKAMURA Kei HASHIMOTO Yoshihiko NANKAKU Keiichi TOKUDA
- 出版者
- The Institute of Electronics, Information and Communication Engineers
- 雑誌
- IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
- 巻号頁・発行日
- vol.E97-D, no.6, pp.1438-1448, 2014-06-01
This paper proposes a novel approach for integrating spectral feature extraction and acoustic modeling in hidden Markov model (HMM) based speech synthesis. The statistical modeling process of speech waveforms is typically divided into two component modules: the frame-by-frame feature extraction module and the acoustic modeling module. In the feature extraction module, the statistical mel-cepstral analysis technique has been used and the objective function is the likelihood of mel-cepstral coefficients for given speech waveforms. In the acoustic modeling module, the objective function is the likelihood of model parameters for given mel-cepstral coefficients. It is important to improve the performance of each component module for achieving higher quality synthesized speech. However, the final objective of speech synthesis systems is to generate natural speech waveforms from given texts, and the improvement of each component module does not always lead to the improvement of the quality of synthesized speech. Therefore, ideally all objective functions should be optimized based on an integrated criterion which well represents subjective speech quality of human perception. In this paper, we propose an approach to model speech waveforms directly and optimize the final objective function. Experimental results show that the proposed method outperformed the conventional methods in objective and subjective measures.
- 著者
- Yasunobu NAKAI Yoshiro ITO Masayuki SATO Kazuhiro NAKAMURA Masanari SHIIGAI Tomoji TAKIGAWA Kensuke SUZUKI Go IKEDA Satoshi IHARA Toshiyuki OKUMURA Masashi MIZUMOTO Koji TSUBOI Akira MATSUMURA
- 出版者
- 社団法人 日本脳神経外科学会
- 雑誌
- Neurologia medico-chirurgica (ISSN:04708105)
- 巻号頁・発行日
- vol.52, no.12, pp.859-864, 2012 (Released:2012-12-25)
- 参考文献数
- 26
- 被引用文献数
- 3
A total of 29 cerebral arteriovenous malformations (AVMs) treated at the University of Tsukuba with multimodality treatment including proton beam (PB) radiotherapy for cerebral AVMs between 2005 and 2011 were retrospectively evaluated. Eleven AVMs were classified as Spetzler-Martin grades I and II, 10 as grade III, and 8 as grades IV and V. For AVMs smaller than 2.5 cm and located on superficial and non-eloquent areas, surgical removal with/without embolization was offered as a first-line treatment. For some small AVMs located in deep or eloquent lesions, gamma knife (GK) radiosurgery was offered. Some AVMs were treated with only embolization. AVMs larger than 2.5 cm were embolized to achieve reduction in size, to enhance the safety of the surgery, and to render the AVM amenable to GK radiosurgery. For larger AVMs located in deep or eloquent areas, PB radiotherapy was offered with/without embolization. Immediately after the treatment, 24 patients exhibited no neurological worsening. Four patients had moderate disability, and 1 patient had severe disability. Three patients suffered brain damage after surgical resection, and 2 patients suffered embolization complications. However, no neurological worsening was observed after either GK radiosurgery or PB radiotherapy, but 3 patients treated by PB radiotherapy suffered delayed hemorrhage. Fractionated PB radiotherapy for cerebral AVMs seems to be useful for the treatment of large AVMs, but careful long-term follow up is required to establish the efficacy and safety.