Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-03-01 09:30 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Multi-Dialect Speech Synthesis with Interpretable Accent latent Variable based on VQ-VAE Kazuki Yamauchi, Yuki Saito, Hiroshi Saruwatari (UTokyo) EA2023-98 SIP2023-145 SP2023-80 |
In this paper, we address two tasks: "Intra-dialect Text-to-Speech (TTS)," aiming to synthesize speech in the same diale... [more] |
EA2023-98 SIP2023-145 SP2023-80 pp.220-225 |
TL |
2023-09-30 13:55 |
Tokyo |
University of Tokyo |
Perception of Pitch Pattern in Unaccented Language
-- Seoul Korean Speakers' Acceptability Judgement -- Yoonkyung Park (UTokyo) TL2023-18 |
(To be available after the conference date) [more] |
TL2023-18 pp.14-18 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-23 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Feature Representation of Japanese Pitch Accent and its Perceptual Adequacy
-- Fundamental Study for Application to Japanese Speech Education -- Ikuyo Masuda-Katsuse (Kindai Univ.) SP2023-3 |
For the purpose of application to Japanese speech education, pitch patterns were modeled by Sequential VAE to obtain a f... [more] |
SP2023-3 pp.8-13 |
TL |
2022-11-26 15:15 |
Yamagata |
Yamagata University |
Process of reanalysis of mispronounced prosody in sentential context Terumichi Ariga (Tokyo Univ.) TL2022-20 |
Although Japanese pitch accent plays a crucial role in access to the mental lexicon in spoken word recognition, listener... [more] |
TL2022-20 pp.11-16 |
EA, SIP, SP, IPSJ-SLP [detail] |
2022-03-02 10:45 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Evaluation of sentence-level generation in Japanese dialect speech synthesis using accent latent variables Kazuya Yufune, Tomoki Koriyama, Shinnosuke Takamichi, Hiroshi Saruwatari (UTokyo) EA2021-79 SIP2021-106 SP2021-64 |
Japanese dialect speech synthesis is useful for personalized speech synthesis systems. However, inability to prepare acc... [more] |
EA2021-79 SIP2021-106 SP2021-64 pp.96-101 |
SP, EA, SIP |
2020-03-03 09:00 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
[Poster Presentation]
An Educational Study on Prosodic Symbols and Their Acoustic Realization Using Japanese End-to-end Speech Synthesis Fuki Yoshizawa (UTokyo), Tadashi Kumano (NHK), Nobuaki Minematsu (UTokyo), Kiyoshi Kurihara (NHK) EA2019-137 SIP2019-139 SP2019-86 |
In order to examine the educational effect of presenting prosodic symbols to learners of Japanese, a method was proposed... [more] |
EA2019-137 SIP2019-139 SP2019-86 pp.207-212 |
MBE, NC (Joint) |
2018-03-13 10:00 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
Rhythm and Stress Patterns Do not Affect Tempo-Keeping Performance of a Finger Tapping Task Ryosei Nagashima, Yutaka Sakaguchi (UEC) NC2017-78 |
The tempo of music performance often drifts (in most cases, it is accelerated) irrespective of the players’ intention. T... [more] |
NC2017-78 pp.63-68 |
SP, IPSJ-SLP, NLC, IPSJ-NL (Joint) [detail] |
2016-12-20 15:10 |
Tokyo |
NTT Musashino R&D |
[Poster Presentation]
Improvement of accent sandhi rules based on accent dictionary for Japanese text-to-speech systems Hiroto Aoyama, Takashi Nose, Akinori Ito (Tohoku Univ.) SP2016-54 |
In order to synthesize more natural speech in Japanese text-to-speech systems, we improved accent sandhi rules. Conventi... [more] |
SP2016-54 pp.31-36 |
SP |
2016-01-14 10:30 |
Kanagawa |
Sunpian Kawasaki |
Performance evaluation of CRF/HMM-based automatic accent labeling for speech synthesis Rina Mashiko, Tomoki Koriyama, Takao Kobayashi (Tokyo Tech) SP2015-85 |
We have proposed an accent type and phrase boundary estimation technique using acoustic and language models represented ... [more] |
SP2015-85 pp.1-6 |
TL |
2015-12-12 16:00 |
Tokyo |
Room 303/304/305, Building #8, Waseda University |
The effect of foreign accents by Japanese on employment-related decisions Lisa Nabei (Tokai Univ.) TL2015-43 |
This study investigates how speakers’ accent impact their employability, specifically the effects of accented English by... [more] |
TL2015-43 pp.19-21 |
TL |
2015-10-04 13:20 |
Tokyo |
WASEDA University |
An N-gram-based approach for input text synthesis depending on text-to-speech system Wang Le, Kacper Radzikowski, Yoshie Osamu (Waseda Univ.) TL2015-34 |
Plenty of researches on text-to-speech(TTS) system have been made, in which prosodic information plays an important role... [more] |
TL2015-34 pp.1-5 |
SP |
2014-11-13 16:55 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Emphasized Accent Phrase Prediction from Advertisement Text towards Expressive Text-to-speech Synthesis Hideharu Nakajima, Hideyuki Mizuno, Sumitaka Sakauchi (NTT) SP2014-95 |
Realizing Expressive Text-to-speech synthesis needs developments of both text processing and the rendering of natural ex... [more] |
SP2014-95 pp.31-36 |
TL |
2014-02-21 17:35 |
Chiba |
Chiba Univ. |
An Analysis in Proficiency of the Accent of Compound Nouns in Japanese by Chinese speaking learners
-- With Special Reference to the "Separated Compound Accent Structer" -- QinWei Huang (Waseda Univ.) TL2013-64 |
Accent patterns of Japanese compounds can be categorized into two types, depending on whether the Compound Accent Rule (... [more] |
TL2013-64 pp.19-24 |
SP, IPSJ-SLP |
2013-12-20 10:10 |
Tokyo |
|
Automatic Estimation of Accent Phrase Boundaries Using Language and Acoustic Models Hiroshi Suzuki, Tomoki Koriyama (Tokyo Tech), Takashi Nose (Tohoku Univ.), Takahiro Shinozaki, Takao Kobayashi (Tokyo Tech) SP2013-89 |
This paper proposes a technique for automatically estimating accent phrase boundaries for text-to-speech synthesis syste... [more] |
SP2013-89 pp.97-102 |
SP, IPSJ-SLP |
2013-12-20 16:40 |
Tokyo |
|
Speech synthesis technologies that supports OJAD
-- An example of applying speech synthesis techniques not to synthsizing speech -- Nobuaki Minematsu, Ibuki Nakamura, Hiroya Hashimoto, Keikichi Hirose (Univ. Tokyo) SP2013-95 |
To support Japanese prosody instruction, the Online Japanese Accent Dictionary (OJAD) has been developed by using NLP an... [more] |
SP2013-95 pp.129-134 |
NLC |
2013-12-05 12:00 |
Tokyo |
Gree Inc. |
Immune Cell Logics of "Dichotomy" and "Dualism" Operate Human Digital Vocal Sign Language and Thought in Human Brain
-- Immune Cells are Mobile Ad-hoc Networking (MANet) Neurons -- Kimiaki Tokumaru (System Engineer) NLC2013-46 |
Human language is a development of spinal reflexes, which seem to be operated NOT by simple electric pulse transfer amon... [more] |
NLC2013-46 pp.69-74 |
SP |
2013-02-28 13:10 |
Aichi |
Daido University |
Development of an online accent dictionary and a reading tutor to support teaching and learning of Japanese prosody Nobuaki Minematsu, Ibuki Nakamura, Masayuki Suzuki (Univ. of Tokyo), Hiroko Hirano (JHFLI), Chieko Nakagawa (Waseda Univ.), Noriko Nakamura (Keio Univ.), Yukinori Tagawa (Waseda Univ.), Hiroya Hashimoto, Keikichi Hirose (Univ. of Tokyo) SP2012-115 |
Through tight collaboration with teachers of Japanese, an online accent dictionary and a reading tutor are developed to ... [more] |
SP2012-115 pp.1-6 |
SP |
2013-02-28 15:00 |
Aichi |
Daido University |
[Poster Presentation]
Autocorrelation-based Representation of Prosodic Feature for Accent Type Recognition Yusuke Onishi, Mitsuru Nakai (Toyama Pref. Univ.) SP2012-123 |
In this paper, we used autocorrelation coefficients of speech wave form as prosodic features. In experiments, we evaluat... [more] |
SP2012-123 pp.29-30 |
IA |
2013-02-15 13:30 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
The Quantum Mechanics of Logic (Digital Linguistics Part-4)
-- Human Consciousness is Immune Networks of Experience/Learning Memories and the Results of their Logical Query Operations (A Hypothesis) -- Kimiaki Tokumaru (System Engineer) IA2012-81 |
Logical thinking sometimes reminds us of dubious syllogism. However, logic circuits in Computer CPUs and life logics of ... [more] |
IA2012-81 pp.67-72 |
SP |
2012-03-09 16:15 |
Saitama |
Riken Brain Science Institute |
Improvement of CRF-Based Accent Sandhi Prediction Using The Features Derived from Accent Rules Shumpei Kobayashi, Shinya Shimizu, Nobuaki Minematsu, Keikichi Hirose (Tokyo Univ.), Hiroko Hirano (Huaqiao Foreign Languages Institute) SP2011-172 |
When developing Japanese text-to-speech (TTS) systems, algorithms to accurately predict accent types of each constituent... [more] |
SP2011-172 pp.95-100 |