===============================================
Special Interest Group on Music and Computer (IPSJ-MUS)
Chair: Rumi Hiraga
Secretary: Tetsuro Kitahara, Tetsuaki Baba, Keiji Hirata, Kazuyoshi Yoshii, Hirokazu Kameoka
===============================================
Technical Committee on Speech (SP)
Chair: Takeshi Kawabata (Kwansei Gakuin Univ.) Vice Chair: Hisashi Kawai (KDDI Labs.)
Secretary: Motoyuki Suzuki (Osaka Inst. of Tech.), Tomoki Toda (NAIST)
Assistant: Yamato Ohtani (Toshiba), Takanobu Oba (NTT)
DATE:
Sat, May 24, 2014 08:50 - 17:45
Sun, May 25, 2014 09:00 - 18:00
PLACE:
TOPICS:
----------------------------------------
Sat, May 24 AM (08:50 - 09:00)
----------------------------------------
(1)/SP 08:50 - 09:00
"Ongaku" Symposium 2014: The 2nd Symposium on Any Topics Related to Acoustics, Audition and Natural Language
Hirokazu Kameoka (Univ. of Tokyo/NTT), Eriko Aiba (UEC), Yasunori Ohishi (NTT), Tetsuro Kitahara (Nihon Univ.), Tatsuya Kitamura (Konan Univ.), Shoei Sato (NHK), Masahito Togami (Hitachi), Tomoki Toda (NAIST), Kazuyoshi Yoshii (Kyoto Univ.)
----------------------------------------
Sat, May 24 AM (09:00 - 09:45)
----------------------------------------
(2)/SP 09:00 - 09:45
[Invited Talk]
Speaker adaptation technologies for speech synthesis and its application to assistive technology
Junichi Yamagishi (NII)
----------------------------------------
Sat, May 24 AM (09:45 - 10:30)
----------------------------------------
(3) 09:45 - 10:30
----------------------------------------
Sat, May 24 AM (10:30 - 11:15)
----------------------------------------
(4)/SP 10:30 - 11:15
[Invited Talk]
Infinite data analysis and Bayesian nonparametrics for audio signal processing
Masahiro Nakano (NTT)
----------------------------------------
Sat, May 24 AM (11:15 - 15:30)
----------------------------------------
----------------------------------------
Sat, May 24 PM (15:30 - 16:15)
----------------------------------------
(5)/SP 15:30 - 16:15
[Invited Talk]
From multimodal spatial hearing to engineering applications to cope with severe disasters
-- Our recent research restuls on spatial acoustic information sciences --
Yo-iti Suzuki, Shuichi Sakamoto (Tohoku Univ.)
----------------------------------------
Sat, May 24 PM (16:15 - 17:00)
----------------------------------------
(6) 16:15 - 17:00
----------------------------------------
Sat, May 24 PM (17:00 - 17:45)
----------------------------------------
(7) 17:00 - 17:45
----------------------------------------
Sun, May 25 AM (09:00 - 09:45)
----------------------------------------
(8)/SP 09:00 - 09:45
[Invited Talk]
Behavioral neurosciences of vocal control and learning
-- using the songbird as a model system --
Ryosuke O. Tachibana (Univ. of Tokyo)
----------------------------------------
Sun, May 25 AM (09:45 - 10:30)
----------------------------------------
(9)/SP 09:45 - 10:30
[Invited Talk]
Machine Translation
-- Why couldn't we do it? Why are we starting to be able to now? --
Graham Neubig (NAIST)
----------------------------------------
Sun, May 25 AM (10:30 - 11:15)
----------------------------------------
(10)/SP 10:30 - 11:15
[Invited Talk]
Applications and Advances of Deep Learning for Automatic Speech Recognition
Yotaro Kubo (Amazon)
----------------------------------------
Sun, May 25 AM (11:15 - 15:30)
----------------------------------------
----------------------------------------
Sun, May 25 PM (15:30 - 16:15)
----------------------------------------
(11)/SP 15:30 - 16:15
[Invited Talk]
R&D of Music Information Retrieval Technology and Issues for its Deployment to Practical Applications
Keiichiro Hoashi (KDDI Labs)
----------------------------------------
Sun, May 25 PM (16:15 - 17:00)
----------------------------------------
(12)/SP 16:15 - 17:00
[Invited Talk]
What Higher-Order Statistics Tell Us?
-- Acoustic Signal Processing Based on Unsupervised Learning --
Hiroshi Saruwatari (Univ. of Tokyo)
----------------------------------------
Sun, May 25 PM (17:00 - 17:45)
----------------------------------------
(13) 17:00 - 17:45
----------------------------------------
Sun, May 25 PM (17:45 - 18:00)
----------------------------------------
----------------------------------------
Sat, May 24 AM (11:30 - 15:30)
----------------------------------------
(14) 11:30 - 15:30
(15) 11:30 - 15:30
(16) 11:30 - 15:30
(17) 11:30 - 15:30
(18) 11:30 - 15:30
(19) 11:30 - 15:30
(20) 11:30 - 15:30
(21) 11:30 - 15:30
(22) 11:30 - 15:30
(23) 11:30 - 15:30
(24) 11:30 - 15:30
(25)/SP 11:30 - 15:30
A Consideration of Evaluation Measurements in Spoken Term Detection
Satoshi Oshima, Yoshiaki Itoh (Iwate Prefectural Univ.)
(26)/SP 11:30 - 15:30
Robustness of Speaker Identification Using Pseudo Pitch Synchronized Phase Information
Yuta Kawakami, Longbiao Wang (Nagaoka Univ. of Tech.), Atsuhiko Kai (Shizuoka Univ.), Seiichi Nakagawa (Toyohashi Univ. of Tech.)
(27)/SP 11:30 - 15:30
Visualization of World Englishes pronunciations from a speaker's self-centered viewpoint using attributes of accent, gender, and age
Yuji Kawase, Nobuaki Minematsu, Daisuke Saito, Keikichi Hirose (UTokyo), Han-Ping Shen (NCKU)
(28) 11:30 - 15:30
(29)/SP 11:30 - 15:30
Native language recognition using machine learning
Ryota Sakagami, Kouki Takeshita, Longbiao Wang, Masahiro Iwahashi (Nagaoka Univ. of Tech)
(30)/SP 11:30 - 15:30
Language recognition in reverberant environments
Kouki Takeshita, Ryota Sakagami, Longbiao Wang, Masahiro Iwahashi (Nagaoka Univ. of Tech.)
(31)/SP 11:30 - 15:30
Discriminative training of acoustic models for system combination
Yuuki Tachioka (Mitsubishi Electric), Shinji Watanabe, Jonathan Le Roux, John R. Hershey (MERL)
(32)/SP 11:30 - 15:30
Distant-talking Speech Recognition with Asynchronous Speech Recording
Shunta Teraoka, Yuma Ueda (Shizuoka Univ.), Longbiao Wang (Nagaoka Univ. of Tech.), Atsuhiko Kai, Taku Fukushima (Shizuoka Univ.)
(33) 11:30 - 15:30
(34) 11:30 - 15:30
(35)/SP 11:30 - 15:30
[研究紹介] A spectrogram-patch-input DNN model for detection and classification of acoustic events robust to speech overlapping scenarios
Miquel Espi, Masakiyo Fujimoto, Yotaro Kubo, Tomohiro Nakatani (NTT)
(36)/SP 11:30 - 15:30
Development of environmental sound collection system using smart devices based on crowd-sourcing approach
Sunao Hara, Akinori Kasai, Masanobu Abe (Okayama Univ.), Noboru Sonehara (NII)
(37)/SP 11:30 - 15:30
ROCKON:Environmental sound collection and recognition system using smartphones
Minori Matsuyama, Takahiko Tsuda, Ryuichi Nisimura, Hideki Kawahara (Wakayama Univ), Junnosuke Yamada (NTT), Toshio Irino (Wakayama Univ)
(38) 11:30 - 15:30
(39) 11:30 - 15:30
(40) 11:30 - 15:30
(41) 11:30 - 15:30
(42)/SP 11:30 - 15:30
Underdetermined Blind Separation of Moving Sources Based on Probabilistic Modeling
Takuya Higuchi, Norihiro Takamune, Tomohiko Nakamura (Univ. of Tokyo), Hirokazu Kameoka (Univ. of Tokyo/NTT)
(43)/SP 11:30 - 15:30
Psychometric functions for across-frequency gap detection
Yousuke Kikuchi, Takako Mitsudo, Nobuyuki Hirose, Shuji Mori (Kyushu Univ.)
(44)/SP 11:30 - 15:30
Deriving the Salience Level of a Target Sound using a Tapping Technique Method
Shunsuke Kidani, Hsin-I Liao, Makoto Yoneya, Makio Kashino, Shigeto Furukawa (NTT)
(45)/SP 11:30 - 15:30
Perception of stop consonants at the beginning of binaurally fused words
Hitomi Kondo, Yousuke Kikuchi, Takako Mitsudo, Nobuyuki Hirose, Shuji Mori (Kyushu Univ.)
(46)/SP 11:30 - 15:30
Effect of interaural time difference for localization of spatially segregated sound
Daisuke Morikawa (JAIST)
(47)/SP 11:30 - 15:30
Acquisition and retention of perceptual cue for size judgment using whispered speech
Koudai Yamamoto, Toshio Irino, Ryuichi Nisimura, Hideki Kawahara (Wakayama Univ.)
----------------------------------------
Sun, May 25 AM (11:30 - 15:30)
----------------------------------------
(48) 11:30 - 15:30
(49) 11:30 - 15:30
(50) 11:30 - 15:30
(51) 11:30 - 15:30
(52) 11:30 - 15:30
(53) 11:30 - 15:30
(54) 11:30 - 15:30
(55) 11:30 - 15:30
(56) 11:30 - 15:30
(57) 11:30 - 15:30
(58)/SP 11:30 - 15:30
Analysis of the Relationship between Pitch and Formant Frequencies in Voice Register Transition
Yasufumi Uezu, Takahiro Furukawa, Tokihiko Kaburagi (Kyushu Univ.)
(59)/SP 11:30 - 15:30
Statistical bandwidth extension using sub-band basis spectrum model
Yamato Ohtani, Masatsune Tamura, Masahiro Morita, Masami Akamine (Toshiba)
(60)/SP 11:30 - 15:30
Text-to-speech prosody synthesis based on probabilistic model for F0 contour
Kento Kadowaki, Tatsuma Ishihara, Nobukatsu Hojo (Univ. of Tokyo), Hirokazu Kameoka (Univ. of Tokyo/NTT)
(61)/SP 11:30 - 15:30
Evaluation of singing voice similarity based on "acoustic singing-structure"
Shun Kojima, Takeshi Saitou, Masato Miyoshi (Kanazawa Univ.)
(62)/SP 11:30 - 15:30
Statistical approach to perceived age control of singing voice
Kazuhiro Kobayashi, Tomoki Toda (NAIST), Tomoyasu Nakano, Masataka Goto (AIST), Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST)
(63)/SP 11:30 - 15:30
A portable application for assistance of vocal sound training by overtone analysis
Iori Sugahara, Takayuki Itoh (Ochanomizu Univ)
(64)/SP 11:30 - 15:30
An Evaluation of a Hybrid Approach to Electrolaryngeal Speech Enhancement Based on Noise Reduction and Statistical Excitation Prediction
Kou Tanaka, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST)
(65)/SP 11:30 - 15:30
Design of voice-enabled web test system for eliminating users' impatience
Chihiro Tafuji, Ryuichi Nisimura, Hideki Kawahara, Toshio Irino (Wakayama Univ.)
(66)/SP 11:30 - 15:30
A joint restricted Boltzmann machine for dictionary learning in sparse-representation-based voice conversion
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.)
(67)/SP 11:30 - 15:30
Speech waveform generation on subband domain
Nobuyuki Nishizawa, Tsuneo Kato (KDDI R&D Labs)
(68)/SP 11:30 - 15:30
A Kana Protocol Recommendation Method for Switch Input Speech Synthesis Systems
Fuming Fang, Takahiro Shinozaki, Takao Kobayashi (Tokyo Tech)
(69)/SP 11:30 - 15:30
Current situations and issues of open-source high-quality speech synthesis system WORLD
Masanori Morise (Univ. of Yamanashi)
(70)/SP 11:30 - 15:30
The Acoustic Feature of the Loudspeaker which used the Reinforced Corrugated Fibreboard for the Enclosure Material
Takuto Isoyama, Yukio Mori (Salesian Polytechnic), Yoshiaki Kiyama
(71)/SP 11:30 - 15:30
Spot-forming method by using two shotgun microphones
Motoyuki Suzuki, Takeshi Honjo (Osaka Inst. of Tech.)
(72)/SP 11:30 - 15:30
Signal processing of ultrasound for osteoporosis diagnosis
-- Modeling, time domain analysis, and frequency domain analysis --
Yoshiki Nagatani (KCCT), Ryosuke O. Tachibana (Univ. of Tokyo)
(73)/SP 11:30 - 15:30
Modulation transfer function based robust method of voice activity detection for noisy reverberant environments
-- Utilization of subband SNR estimation --
Shota Morita, Masashi Unoki (JAIST), Xugang Lu (NICT), Masato Akagi (JAIST)
(74)/SP 11:30 - 15:30
Systematic study on kawaii products (The seventeenth report)
-- Basic study for Kawaii sound --
Michiko Ohkura, Ryo Kanno (Shibaura Inst. Tech.)
(75)/SP 11:30 - 15:30
The basic mechanisms for perception of simultaneity, stream segregation, and temporal order for auditory stimuli
Satoshi Okazaki, Makoto Ichikawa (Chiba Univ.)
(76) 11:30 - 15:30
(77) 11:30 - 15:30
(78)/SP 11:30 - 15:30
[研究紹介] Adaptive adjustment of local temporal structure in song of Bengalese finches
Ryosuke O. Tachibana, Neal A. Hessler, Kazuo Okanoya (Univ. of Tokyo)
(79)/SP 11:30 - 15:30
Modulation of the Temporal Dynamics of Microsaccades with the Presentation of Salient Sounds
Makoto Yoneya, Hsin-I Liao, Shunsuke Kidani, Shigeto Furukawa (NTT), Makio Kashino (NTT/Tokyo Tech)
# Information for speakers
Invited Talk will have 35 minutes for presentation and 10 minutes for discussion.
Poster Presentation will have 225 minutes for presentation.
=== Special Interest Group on Music and Computer (IPSJ-MUS) ===
=== Technical Committee on Speech (SP) ===
# FUTURE SCHEDULE:
Thu, Jun 19, 2014 - Fri, Jun 20, 2014: [Fri, Apr 11]
Thu, Jul 24, 2014 - Sat, Jul 26, 2014: Hotel Hanamaki [Wed, May 14], Topics: Speech recognition and understanding, dialog system, etc.
Aug, 2014: Recess
Last modified: 2014-05-23 15:06:55
|
Notification: Mail addresses are partially hidden against SPAM.
|