poster_en.pdf
, T. Ishihara, N. Hojo, and H. Kameoka,"Speech prosody generation for text-to-speech synthesis based
https://www.rd.ntt/cs/event/openhouse/2015/exhibition/16/poster_en.pdf
Speech information processing | NTT R&D Website
Laboratories focus on research and development of "speech recognition" and "speech synthesis". Speech
https://www.rd.ntt/e/hil/category/voice/
NTT Communication Science Laboratories Open House 2015
has realized the analysis/synthesis framework focusing on the 'phonemic' factor of speech, the aim of
https://www.rd.ntt/cs/event/openhouse/2015/exhibition/16/index_en.html
音声情報処理 | NTT R&D Website
, ``ENHANCEMENT OF TEXT-PREDICTING STYLE TOKEN WITH GENERATIVE ADVERSARIAL NETWORK FOR EXPRESSIVE SPEECH SYNTHESIS
https://www.rd.ntt/hil/category/voice/
Speech and Audio Signal Modeling | NTT Communication Science Laboratories | NTT R&D Website
speech signal processing problems, including speech analysis, synthesis, modification, coding, and
https://www.rd.ntt/e/cs/team_project/media/recognition/research_media03.html
NTT Communication Science Laboratories Open House 2018
between the speech recognition and synthesis techniques and the human brain mechanisms will be discussed
https://www.rd.ntt/cs/event/openhouse/2018/talk/research4/index_en.html
P04_leaf_e.pdf
devices, to utilize user's background and contextual information Speech synthesis technology capable of
https://www.rd.ntt/forum/2023/doc/P04_leaf_e.pdf
Program of WASPAA2007
Bertrand David, Roland Badeau [TP1-20] Speech-To-Singing Synthesis: Converting Speaking Voices to Singing
https://www.rd.ntt/cs/team_project/icl/signal/waspaa2007/program.html
poster_en_17.pdf
postfilter for statistical parametric speech synthesis," in Proc. 2017 IEEE International Conference on
https://www.rd.ntt/cs/event/openhouse/2017/exhibition/17/poster_en_17.pdf
Video Library | Service Innovation Laboratory Group | NTT R&D Website
training algorithm of a deep neural network Speech synthesis technology to generate speech with various
https://www.rd.ntt/e/svlab/video_library/
AI|NTT R&D Website
Videos Speech synthesis technology to generate speech with various characteristics and rich
https://www.rd.ntt/e/ai/
Media Information Laboratory Past news | NTT Communication Science Laboratories | NTT R&D Website
-resistant variational autoencoder” has been accepted to ISCA Speech Synthesis Workshop (SSW2023). Kou Tanaka
https://www.rd.ntt/e/cs/team_project/media/past_news.html
事象モデリング研究グループ|NTTコミュニケーション科学基礎研究所|NTT R&D Website
Adversarial Network-Based Speech Synthesis. Proc. IEEE International Conference on Acoustics, Speech, and
https://www.rd.ntt/cs/team_project/media/computational_modeling/
Computational Modeling Research Group | NTT Communication Science Laboratories | NTT R&D Website
Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
https://www.rd.ntt/e/cs/team_project/media/computational_modeling/
program_for_web.pdf
Badeau [TP1-20] Speech-To-Singing Synthesis: Converting Speaking Voices to Singing Voices by Controlling
https://www.rd.ntt/cs/team_project/icl/signal/waspaa2007/program_for_web.pdf
0047.pdf
SPEECH ENHANCEMENT EMPLOYING ADAPTIVE BEAMFORMER WITH RECURSIVELY UPDATED SOFT CONSTRAINTS Hai Q
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0047.pdf
スライド 1
), 2017.[2] T. Kaneko, K. Hiramatsu, K. Kashino,“Generative Adversarial Image Synthesis with Decision Tree
https://www.rd.ntt/cs/event/openhouse/2018/exhibition/21/poster_en_21.pdf
メディア情報研究部 過去のニュース|NTTコミュニケーション科学基礎研究所|NTT R&D Website
Speech Synthesis Workshop (SSW) に採録されました。 Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, “PRVAE-VC: Non
https://www.rd.ntt/cs/team_project/media/past_news.html
0067.pdf
convolutive mixtures of speech. This is moti- vated by the drawback of frequency-domain BSS, i.e., when a long
https://www.rd.ntt/cs/team_project/icl/signal/ica2003/cdrom/data/0067.pdf
poster.pdf
-to-speech synthesis based on generative model of F0 contours," in Proc. The 15th Annual Conference of
https://www.rd.ntt/cs/event/openhouse/2015/exhibition/16/poster.pdf
Microsoft Word - timetable.doc
Synthesis Conference House 10:00 10:20 Break West Dining Room Break West Dining Room Break West Dining Room
https://www.rd.ntt/cs/team_project/icl/signal/waspaa2007/Timetable.pdf
pp.dvi
helps in dis- tinguishing speakers. We introduce a speech synthesis model that can be identified using
https://www.rd.ntt/cs/team_project/icl/signal/ica2003/cdrom/data/0177.pdf
NTT Communication Science Laboratories Open House 2018 Program
/1 (Fri) 13:50 - 14:30 Speech production and perception share common brain pathways ∼Investigation of
https://www.rd.ntt/cs/event/openhouse/2018/program_en.html
NTT Communication Science Laboratories Open House 2018
Nishino, Innovative Communication Laboratory 13:50 - 14:30 Speech production and perception share common
https://www.rd.ntt/cs/event/openhouse/2018/en_simple/index_en.html
poster_en_16.pdf
adversarial network-based postfilter for statistical parametric speech synthesis,” in Proc. The 42nd IEEE
https://www.rd.ntt/cs/event/openhouse/2017/exhibition/16/poster_en_16.pdf
0039.pdf
information,” in ICASSP 2002, vol.1, pp. 541-544 [4] B.S. Atal and S.L. Hanauer,“Speech analysis and synthesis
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0039.pdf
Microsoft PowerPoint - C_パネル一覧0501.pptx
statistical parametric speech synthesis," in Proc. 2017 IEEE International Conference on Acoustics, Speech and
https://www.rd.ntt/cs/event/openhouse/2017/exhibition/17/poster17.pdf
Microsoft PowerPoint - C_パネル一覧0501.pptx
,“Generative adversarial network-based postfilter for statistical parametric speech synthesis,” in Proc. The 42
https://www.rd.ntt/cs/event/openhouse/2017/exhibition/16/poster16.pdf
Chat Dialogue Technology | NTT Communication Science Laboratories | NTT R&D Website
Speech Synthesis for Japanese Elderly Adults, Conference of the Oriental COCOSDA International Committee
https://www.rd.ntt/e/cs/team_project/icl/ir/research_innovative08.html
What is Digital Twin Computing?|NTT R&D Website
recognition. Speech Synthesis The question here is how and to what extent textual information can be converted
https://www.rd.ntt/e/iown/0003.html
Recognition Research Group | NTT Communication Science Laboratories | NTT R&D Website
-based speech synthesis considering dialogue-act information and its evaluation with respect to
https://www.rd.ntt/e/cs/team_project/media/recognition/
0002.pdf
SPEECH DEREVERBERATION VIA SUB-BAND IMPLEMENTATION OF SUBSPACE METHODS Sharon Gannot Faculty of
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0002.pdf
main.dvi
- aration,” Proceedings of ICA2003, pp.505–510, 2003.[8] S. Furui,“Digital Speech Processing, Synthesis and
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0045.pdf
メディア認識研究グループ|NTTコミュニケーション科学基礎研究所|NTT R&D Website
. Hojo, Y. Ijima, H. Sugiyama, N. Miyazaki, T. Kawanishi, and K. Kashino, "DNN-based speech synthesis
https://www.rd.ntt/cs/team_project/media/recognition/
Media Information Laboratory | NTT Communication Science Laboratories | NTT R&D Website
and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis. Proc. IEEE
https://www.rd.ntt/e/cs/team_project/media/
H1-H4
network-based postfilter for statistical parametric speech synthesis,” in Proc. 42nd IEEE International
https://www.rd.ntt/cs/event/openhouse/2017/talk/research2/talk_kaneko.pdf
Major issues and research trends in the evolution of artificial intelligence (AI)|NTT R&D Website
realistic speech synthesis technology, users can enjoy communication as if they were talking with Ms
https://www.rd.ntt/e/ai/0001.html
iwaenc2003_2.dvi
quality, consistent analysis-synthesis method with re-opti- mization of amplitude and frequency parameters
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0052.pdf
メディア情報研究部|NTTコミュニケーション科学基礎研究所|NTT R&D Website
Discriminator for Generative Adversarial Network-Based Speech Synthesis. Proc. IEEE International Conference on
https://www.rd.ntt/cs/team_project/media/
0085.pdf
STATISTICAL METHODS FOR THE ENHANCEMENT OF NOISY SPEECH Rainer Martin Institute of Communication
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0085.pdf
0060.pdf
REGULARIZED OPTIMIZATION WITH SPECTRAL SMOOTHING FOR SPEECH SPECTRAL ESTIMATION Karsten Vandborg Sø
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0060.pdf
DemoSessionProgram.pdf
Delay Estimation and Speech Dereverberation Yuanqing Lin (GRASP Laboratory, Department of Electrical and
https://www.rd.ntt/cs/team_project/icl/signal/waspaa2007/DemoSessionProgram.pdf
Human Information Science Laboratory | NTT Communication Science Laboratories | NTT R&D Website
willingness to buy model from advertising speech,“ Acoustical Science and Technology. [https://doi.org/10.1250
https://www.rd.ntt/e/cs/team_project/human/
paper.dvi
composed of clean near speech % ��"! , local background noise ) ��+! , and acoustic echo ,��+! . The echo
https://www.rd.ntt/cs/team_project/icl/signal/iwaenc03/cdrom/data/0016.pdf
人間情報研究部|NTTコミュニケーション科学基礎研究所|NTT R&D Website
in an emotion-mediated willingness to buy model from advertising speech,“ Acoustical Science and
https://www.rd.ntt/cs/team_project/human/
0044.pdf
) [4] J.L. Flanagan:"Speech Analysis Synthesis and Perception, 2nd Edition," Springer, 1972. tsumori 6
https://www.rd.ntt/cs/team_project/icl/signal/ica2003/cdrom/data/0044.pdf
0076.pdf
appli- cations, e.g., speech/image enhancement and/or recognition, noise reduction and so on. However
https://www.rd.ntt/cs/team_project/icl/signal/ica2003/cdrom/data/0076.pdf
articleICA03.dvi
, Analysis-Synthesis Group IRCCyN, ADTS Group IRISA, METISS Project 1, place Igor Stravinsky 1, rue de la No
https://www.rd.ntt/cs/team_project/icl/signal/ica2003/cdrom/data/0085.pdf
oh2017_booklet.pdf
,“Generative adversarial network-based postfilter for statistical parametric speech synthesis,” in Proc. 42nd
https://www.rd.ntt/cs/event/openhouse/2017/download/oh2017_booklet.pdf
Keynote Speech 1|NTT R&D FORUM 2023 — IOWN ACCELERATION Report
people who have lost their ability to speak, we are working on cross-lingual speech synthesis technology
https://www.rd.ntt/e/forum/2023/keynote_1.html
Report on the NTT R&D Forum 2018 (Autumn) | NTT R&D Website
using speech synthesis techniques realized through the study of old broadcast content via a neural
https://www.rd.ntt/e/forum/forum2018_autumn.html
論文|NTT物性科学基礎研究所|NTT R&D Website
, A. Tanaka, Y. Kawai, and S. Imamura "Synthesis Of Alkali-Soluble Silicone Resin Suitable For Resist
https://www.rd.ntt/brl/result/publications/paper_1990.html
Publications | NTT Basic Research Laboratories | NTT R&D Website
. Imamura "Synthesis Of Alkali-Soluble Silicone Resin Suitable For Resist Material In Microlithography
https://www.rd.ntt/e/brl/result/publications/paper_1990.html
2020_booklet_en.pdf
, Speech, and Signal Processing (ICASSP), pp. 6594-598, May 2020.[2] N. Tawara, H. Kamiyama, S. Kobashikawa
https://www.rd.ntt/cs/event/openhouse/2020/download/2020_booklet_en.pdf
論文|NTT物性科学基礎研究所|NTT R&D Website
based on template adaptation and music stream extraction" Speech Commun. 27 (3-4) 337-349 (1999). T
https://www.rd.ntt/brl/result/publications/paper_1999.html
Publications | NTT Basic Research Laboratories | NTT R&D Website
identification system for ensemble music based on template adaptation and music stream extraction" Speech Commun
https://www.rd.ntt/e/brl/result/publications/paper_1999.html
oh1013_booklet.pdf
speech recognition: past, present and future みんなの会話を聞き取るコンピュータを目指して~複数人会話音声認識研究の現状と今後の展望~■会話音声認識の研究 コミ
https://www.rd.ntt/cs/event/openhouse/2013/download/oh1013_booklet.pdf
article2-ICA03.dvi
Emmanuel Vincent Cédric Févotte Laurent Benaroya IRISA, METISS Project IRCAM, Analysis-Synthesis Group
https://www.rd.ntt/cs/team_project/icl/signal/ica2003/cdrom/data/0014.pdf
論文|NTT物性科学基礎研究所|NTT R&D Website
superconductors" Phys. Rev. B 63 (10), 100507 (2001). J. R. Koe, M. Motonaga, M. Fujiki, and R. West "Synthesis
https://www.rd.ntt/brl/result/publications/paper_2001.html
Publications | NTT Basic Research Laboratories | NTT R&D Website
superconductors" Phys. Rev. B 63 (10), 100507 (2001). J. R. Koe, M. Motonaga, M. Fujiki, and R. West "Synthesis
https://www.rd.ntt/e/brl/result/publications/paper_2001.html
final.dvi
International Con- ference on Acoustics, Speech and Signal Processing, 1999.[3] Masataka Goto and Yoichi Muraoka
https://www.rd.ntt/cs/team_project/icl/signal/ica2003/cdrom/data/0057.pdf
論文|NTT物性科学基礎研究所|NTT R&D Website
(1994). T. Kawabata "Predictor Codebook For Speaker-Independent Speech Recognition" Syst. Comput. Jpn
https://www.rd.ntt/brl/result/publications/paper_1994.html
Publications | NTT Basic Research Laboratories | NTT R&D Website
(1994). T. Kawabata "Predictor Codebook For Speaker-Independent Speech Recognition" Syst. Comput. Jpn
https://www.rd.ntt/e/brl/result/publications/paper_1994.html
Dr.Naonori Ueda | NTT R&D Website
Extensions of Non-negative Matrix Factorization with Complex-valued Data," IEEE Transactions on Audio, Speech
https://www.rd.ntt/e/organization/researcher/fellow/f_003.html
上田 修功 | NTT R&D Website
Audio, Speech, and Language Processing, Vol.21, No.5, pp.971-982, 2013. [IEEE Copyright Notice] Iwata, T
https://www.rd.ntt/organization/researcher/fellow/f_003.html
Prev
Next