Search Results 1-20 of 41

  • 1 / 3
  • Speaker's Localization in Meeting Using Speech Sound  [in Japanese]

    福島 潤 , 大山 真司

    センシングフォーラム資料 36, 6p, 2019-08-29

  • Lip-reading effects seen in auditory evoked fields (AEFs)  [in Japanese]

    Kawase Tetsuaki

    … <p>Visual speech information presented synchronously with speech sound can affect speech perception. … However, speech processing in the auditory cortex, an earlier processing site than the STS in auditory signal processing, might be modulated by the visual effects conveyed via the direct corticocortical (visual cortex to auditory cortex) pathway, which does not involve the STS. …

    Transactions of Japanese Society for Medical and Biological Engineering 55Annual(4PM-Abstract), 374-374, 2017

    J-STAGE 

  • Effects of speaker's and listener's acoustic environments on speech intelligibility and annoyance

    Kubo Rieko , Morikawa Daisuke , Akagi Masato

    Speech signal modification to increase intelligibility in noisy environments may cause discomfort in quieter environments. … Human speech production in noise is known to improve intelligibility in noise. … The speech modification algorithm which use rules obtained from human speech production are expected to meet the demand for both of high intelligibility and reducing discomfort in various acoustic environments. …

    Inter-noise 2016, 171-176, 2016-08-21

    IR 

  • Evaluation of Speech Interval Detection and Face Orientation Estimation based on Sound Directions by Multiple Microphone Arrays and Human Positions  [in Japanese]

    Ishi Carlos T. , Even Jani , Hagita Norihiro

    … We developed a system for detecting the speech intervals of multiple speakers and estimating the face orientation during the detected speech intervals by combining information of sound directions from multiple microphone arrays and human positions. …

    Journal of the Robotics Society of Japan 34(3), 199-204, 2016

    J-STAGE 

  • Evaluation of usefulness of speech visualization system for articulation pattern analysis in patients with mandibular prognathism  [in Japanese]

    SHINNAKASU Mana , HIRAHARA Narihiro , SAKATA Tadashi , GOMI Akinori , NOZOE Etsuro , UEDA Yuichi , NAKAMURA Norifumi

    … Instruments for auditory assessment or sound analysis were conventionally used to evaluate abnormal speech sounds. … However, since the representations by these subjective or objective methods are ambiguous and difficult to understand, they are not practical for feedback to patients in speech therapy. …

    Japanese Journal of Oral and Maxillofacial Surgery 62(1), 3-9, 2016

    J-STAGE  Ichushi Web 

  • Intonation in German Speech with Different Emotions  [in Japanese]

    富永 晶子

    … This study focused on how pitch contours in German speech correlate with different emotions of the speaker, because intonation contributes not only to communicating certain information but also to expressing a speaker's emotions. … It is obvious that speakers express their emotions with the proper intonation well integrated into their speech. …

    言語科学論集 (22), 87-106, 2016

    IR  DOI 

  • English-Read-By-Japanese Speech Synthesis Preserving Speaker Individuality Based on Partial Correction of Prosody and Phonetic Sounds and Effects of English Proficiency Level on Its Performance  [in Japanese]

    大島 悠司 , 高道 慎之介 , 戸田 智基 , Sakriani Sakti , Graham Neubig , 中村 哲

    … Cross-lingual speech synthesis for generating naturally sounding English speech uttered by Japanese speakers based on voice conversion and HMM-based speech synthesis tends to cause the degradation of speaker individuality in synthetic speech compared to intra-lingual speech synthesis. …

    IPSJ SIG Notes 2015-SLP-105(3), 1-6, 2015-02-20

  • A Noise Reduction Method Using Joint Distribution of Observed Signals

    Ishibashi T. , Tajiri Y. , Inoue K. , Gotanda H.

    … The proposed method can reduce noise signals even when the number of sound sources is larger than that of observed mixture signals. … By several simulations, the proposed method can extract the target speech signal from multi speaker's utterance sounds. …

    Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications 2014(0), 367-372, 2014

    J-STAGE 

  • Interaction between hearing and speaking by aging  [in Japanese]

    MIZUMACHI Mitsunori

    … In the aging society, it is difficult for the elderly to establish smooth speech communication. … The high-frequency hearing loss seriously decreases our ability in hearing consonants of words and sound source separation in noisy environments. … Concerning the ability of speech perception, it is possible to roughly estimate the speaker's age, when someone speaks. …

    IEICE technical report. Welfare Information technology 113(272), 61-66, 2013-10-26

  • One-model Speech Recognition and Synthesis System based on Articulatory  [in Japanese]

    KIMURA Masashi , ONODA Takayuki , IRIBE Yurie , KATSURADA Kouichi , NITTA Tsuneo

    Speech recognition (SR) and speech synthesis (SS) based on one-model of articulatory movement HMMs that are commonly applied to both an SR module and an SS module are described. … In the SS module, the speaker-invariant HMMs are applied to generate an articulatory feature (AF) sequence, and then, after converting AFs into vocal tract parameters by using a multi-layer neural network (MLN), a speech signal is synthesized by an LSP (Line Spectrum Pairs) digital filter. …

    IEICE technical report 111(153), 1-6, 2011-07-14

    References (11)

  • A Voice Conversion Method Using Individuality of Sound Source  [in Japanese]

    UEMURA Akihito , TOYAMA Jun

    … We treat the residuals of linear predictive coding as source signal to represent a target speaker individuality. … Objective experimental results indicate that the power spectrum of the speech converted by our method is similar to a target speaker's one. …

    IEICE technical report 110(356), 159-163, 2010-12-13

    References (8)

  • A Voice Conversion Method Using Individuality of Sound Source  [in Japanese]

    UEMURA Akihito , TOYAMA Jun

    … We treat the residuals of linear predictive coding as source signal to represent a target speaker individuality. … Objective experimental results indicate that the power spectrum of the speech converted by our method is similar to a target speaker's one. …

    IEICE technical report 110(357), 159-163, 2010-12-13

    References (8)

  • The effects of auditory repetition priming and acoustical attributes on speech perception  [in Japanese]

    SASAKI Yasunari , MURAO Mika , YAMAMOTO Seiichi

    … This study investigated the roles of implicit memory and acoustical features on speech perception by means of changing the fundamental frequency and formant frequency of nonsense words presented in a study phase. … It indicates that acoustic properties such as sound patterns of the words or speaker's characteristics of the speech sounds played critical roles in auditory priming. …

    Proceedings of the Japanese Society for Cognitive Psychology 2009(0), 59-59, 2009

    J-STAGE 

  • Evaluation of Speaking-Aid System with Voice Conversion for Laryngectomees Toward Its Use in Practical Environments

    Keigo Nakamura , Tomoki Toda , Yoshitaka Nakajima , Hiroshi Saruwatari , Kiyohiro Shikano

    … The proposed system employs a sound source unit generating extremely small signals to keep them from annoying other persons, and then it statistically converts articulated signals captured with a bodyattached microphone into natural speech. … We have so far shown the effectiveness of the proposed system using speech data imitated by a non-laryngectomee, which have recorded in a sound proof room. …

    2008-09

    IR 

  • A study on implementation of mobile-phone with speaker verification  [in Japanese]

    HAMANO Yutaka , ICHINO Masatsugu , YAMAZAKI Yasushi , TSURUMARU Kazuhiro , KOMATSU Naohisa

    … In this paper we propose a speaker verification method based on CELP (Code Excited Linear Prediction) speech coding scheme. … The proposed method utilizes CELP parameters which are used in speech coding schemes for mobile phone networks or IP networks, and verifies a speaker only with the encoded speech. …

    IEICE technical report 107(347), 51-56, 2007-11-14

    References (7)

  • A study on implementation of mobile-phone with speaker verification  [in Japanese]

    HAMANO Yutaka , ICHINO Masatsugu , YAMAZAKI Yasushi , TSURUMARU Kazuhiro , KOMATSU Naohisa

    … In this paper we propose a speaker verification method based on CELP (Code Excited Linear Prediction) speech coding scheme. … The proposed method utilizes CELP parameters which are used in speech coding schemes for mobile phone networks or IP networks, and verifies a speaker only with the encoded speech. …

    IEICE technical report 107(345), 51-56, 2007-11-14

    References (7)

  • Hybrid Voice Conversion of Unit Selection and Generation Using Prosody Dependent HMM

    OKUBO Tadashi , MOCHIZUKI Ryo , KOBAYASHI Tetsunori

    … In the proposed method, the HMM-based unit selection selects the most likely unit for the required phoneme context from the target speaker's corpus when candidates of the target unit exist in the corpus. … To show the effectiveness of the proposed method, sound quality and speaker individuality tests were conducted. …

    IEICE transactions on information and systems 89(11), 2775-2782, 2006-11-01

    References (14)

  • Accuracy improvement in speech sound propagation measurement using logarithmic temporal manipulation  [in Japanese]

    MORISE Masanori , IRINO Toshio , KAWAHARA Hideki

    … A new procedure to improve accuracy in empirical transfer function estimation method is proposed for investigating speech sound propagation. … In our previous work based on cross spectrum method, vowel dependencies of empirical transfer functions from a lip reference point to observation points around speaker's head were found. …

    Technical report of IEICE. EA 105(348), 43-48, 2005-10-14

    References (13)

  • Research on a system that corrects the uttered sound with vocal feature maintained. (1^<st>. Report) : Basic experiment on single mora sound  [in Japanese]

    YABU Ken-ichiro , IGOSHI Masanori

    … One of our authors has articulation handicap and feels strongly the importance of the voice information in conversation that cannot be expressed with texts We are considering about a system which makes the indistinct sound clear and which keeps the speaker's feature of voice as much as possible. … The author's indistinct sound was used for the experiment as a model case. …

    IEICE technical report. Welfare Information technology 105(186), 21-26, 2005-07-07

    References (10)

  • Impression of Speaker's Personality and the Naturalistic Qualities of Speech : Speech Rate and Pause Duration  [in Japanese]

    UCHIDA TERUHISA

    … The present study investigated the relation between temporal structures of speech and listeners' impressions of the speaker's personality. … The following speech stimuli were manipulated in paragraph-length speeches: speech durations of sound region (65%-147%) and duration of pause (56%-178%). …

    The Japanese journal of educational psychology. 53(1), 1-13, 2005-03

    NDL Digital Collections  Cited by (5)

  • 1 / 3
Page Top