2008 書籍

  1. 峯松信明，
    "「あ」という声を聞いて母音「あ」と同定する能力は音声言語運用に必要か？　〜音声認識研究からの一つの提言〜"，
    日本語学4月号，p.187-197，明治書院 (2008-4)
  2. N. Minematsu and T. Nishimura,
    "Consideration of infants' vocal imitation through modeling speech as timbre-based melody,"
    in New Frontiers in Artificial Intelligence, LNAI4914, pp.26-39, Springer (2008)

2008 雑誌論文

  1. Md. K. I. Molla, K. Hirose, and N. Minematsu,
    "The robustness and applicability of audio source separation from single mixtures,"
    Acoustics Australia, vol.36, no.2, pp.23-27 (2008-8)
  2. X. D. Wang, K. Hirose, J. S. Zhang, and N. Minematsu,
    "Tone recognition of continuous Mandarin speech based on tone nucleus model and neural network,"
    Trans. IEICE, vol.E91-D, no.6, pp.1748-1755 (2008-6)
  3. T. Kamada, N. Minematsu, T. Osanai, H. Makinae, and M. Tanimoto,
    "Speaker verification in realistic noisy environment in forensic science,"
    Trans. IEICE, vol.E91-D, no.3, pp.558-566 (2008-3)
  4. 村上隆夫，峯松信明，広瀬啓吉，
    "音声の構造的表象に基づく日本語孤立母音系列を対象とした音声認識"，
    電子情報通信学会論文誌，vol.J91-A，no.2，pp.181-191 (2008-2)
  5. M. Watanabe, K. Hirose, Y. Den, and N. Minematsu,
    "Filled pauses as cues to the complexity of upcoming phrases for native and non-native listeners,"
    Speech Communication, vol.50, pp.81-94 (2008-1)

2008 国際会議論文

  1. D. Luo, N. Minematsu, Y. Yamauchi, and K. Hirose,
    "Automatic assessment of non-native shadowed utterances,"
    Proc. Int. Symposium on Chinese Spoken Language Processing (ISCSLP), pp.41-44 (2008-12)
  2. K. Hirose, Q. Sun, N. Minematsu,
    "Corpus-based synthesis of Madarin speech with F0 contours generated by superposing tone contours on rule-generated phrase components,"
    Proc. IEEE Workshop on Spoken Language Technology (SLT), pp.33-36 (2008-12)
  3. N. Minematsu, D. Saito, and K. Hirose,
    "Experimenal study of structure-to-speech conversion -- an implementation of infant-like vocal imitation --,"
    Proc. Int. Conf. Signal Processing (ICSP), pp.651-654 (2008-10)
  4. K. Hirose, K. Ochi, and N. Minematsu,
    "Corpus-based generation of F0 contours of Japanese based on the generation process model and its control for prosodic focus,"
    Proc. Int. Conf. Signal Processing (ICSP), pp.647-650 (2008-10)
  5. Md. K. I. Molla, K. Hirose, and N. Minematsu,
    "Robust determination of periodic correlation of speech signals using empirical mode decomposition and higher-order spectra,"
    Proc. Asia-Pacific Conference on Communications (APCC), CD-ROM (2008-10)
  6. Md. K. I. Molla, K. Hirose, and N. Minematsu,
    "Robust voiced/unvoiced speech classification using empirical mode decomposition and periodic correlation model,"
    Proc. INTERSPEECH, pp.2530-2533 (2008-9)
  7. K. Ochi, K. Hirose, and N. Minematsu,
    "Control of prosodic focus in corpur-based generation of fundamental frequency based on the generation process model,"
    Proc. INTERSPEECH, pp.1216 (2008-9)
  8. D. Luo, N. Shimomura, N. Minematsu, Y. Yamauchi, and K. Hirose,
    "Automatic pronunciation evaluation of language learners' utterances generated through shadowing,"
    Proc. INTERSPEECH, pp.2807-2810 (2008-9)
  9. D. Saito, S. Asakawa, N. Minematsu, and K. Hirose,
    "Structure to speech -- speech generation based on infant-like vocal imitation --,"
    Proc. INTERSPEECH, pp1837-1840 (2008-9)
  10. D. Saito, N. Minematsu, and K. Hirose,
    "Decomposition of rotational distortion caused by VTL difference using eigenvalues of its transofmation matrix,"
    Proc. INTERSPEECH, pp.1361-1364 (2008-9)
  11. Y. Qiao and N. Minematsu,
    "f-divergence is a generalized invariant measure between distributions,"
    Proc. INTERSPEECH, pp.1349-1352 (2008-9)
  12. Y. Qiao and N. Minematsu,
    "Metric learning for unsupervised phoneme segmentation,"
    Proc. INTERSPEECH, pp.1060-1063 (2008-9)
  13. K. Hirose, Q. Sun, N. Minematsu,
    "Synthesis of F0 contours for Mandarin speech by superposing corpus-generated tone contours on rule-generated phrase components,"
    Proc. Int. Conf. on Speech Analysis, Synthesis, and Recognition (SASR), Plenary Talk (2008-9)
  14. D. Luo, N. Minematsu, Y. Yamauchi, K. Hirose,
    "Automatic assessment of utterances shadowed by learners using speech technologies,"
    Proc. Int. Workshop on Language and Speech Science (2008-9)
  15. M. Ma, H. Hirano, K. Hirose, N. Minematsu,
    "A CALL system for Japanese learners of Mandarin speech adaptive to learners' proficiency,"
    Proc. Int. Workshop on Language and Speech Science (2008-9)
  16. N. Minematsu, K. Kamata, M. Takazawa, K. Takeuchi, S. Asakawa, T. Makino, Y. Yamauchi, T. Nishimura, K. Hirose,
    "Pronunciation clinic -- which part of your pronunciation to correct at first to become like your model speaker? --,"
    WorldCALL, Courseware Session (2008-8)
  17. N. Minematsu,
    "Are language learners myna birds? -- a note of warning from a serious speech engineer --,"
    WorldCALL, Poster Session (2008-8)
  18. N. Minematsu and T. Nishimura,
    "Speech as timbre-based melody -- What in parants' voices do infants imitate acoustically? --,"
    Proc. Int. Conf. Language, Music, and the Mind, Paper Session (2008-7)
  19. N. Minematsu, T. Nishimura, D. Saito, S. Asakawa, Y. Qiao,
    "Holistic and prosodic representation of the segmental aspect of speech,"
    Proc. Int. Conf. Speech Prosody, pp.169-172 (2008-5)
  20. Q. Sun, K. Hirose, N. Minematsu,
    "Improved prediction of tone components for F0 contour generation of Mandarin speech based on the tone nucleus model,"
    Proc. Int. Conf. Speech Prosody, pp.95-98 (2008-5)
  21. K. Hirose, Q. Sun, and N. Minematsu,
    "Generation of F0 contours for Mandarin speech in combination with rule-based and corpus-based methods,"
    Proc. The 8th Phonetic Conference of China and Int. Symposium on Phonetic Frontiers, CD-ROM (2008-4)
  22. N. Minematsu,
    "Training of pronunciation as learning of the sound system embedded in the target language,"
    Proc. The 8th Phonetic Conference of China and Int. Symposium on Phonetic Frontiers, CD-ROM (2008-4)
  23. Y. Qiao, W. Wang, N. Minematsu, J. Liu, X. Tang
    "Phase singularities for image representation and matching,"
    Proc. Int. Conf. Acoustics, Speech, & Signal Processing (ICASSP'2008), pp.885-888 (2008-4)
  24. Y. Qiao, N. Shimomura, N. Minematsu,
    "Unsupervised optimal phoneme segmentation: objectives, algorithm and comparisons,"
    Proc. Int. Conf. Acoustics, Speech, & Signal Processing (ICASSP'2008), pp.3989-3992 (2008-4)
  25. D. Saito, R. Matsuura, S. Asakawa, N. Minematsu, K. Hirose,
    "Directional dependency of cepstrum on vocal tract length,"
    Proc. Int. Conf. Acoustics, Speech, & Signal Processing (ICASSP'2008), pp.4485-4488 (2008-4)
  26. S. Asakawa, N. Minematsu, K. Hirose,
    "Multi-stream parameterization for structural speech recognition,"
    Proc. Int. Conf. Acoustics, Speech, & Signal Processing (ICASSP'2008), pp.4097-4100 (2008-4)
  27. A. Rebordao, M. K. I. Molla, K. Hirose, N. Minematsu,
    "An adaptive speech denoising system based on ICA and voice activity detection,"
    Proc. Int. Workshop on Nonlinear Circuits and Signal Processing, pp.228-231 (2008-3)
  28. E. Deger, M. K. I. Molla, K. Hirose, N. Minematsu,
    "Hard and soft thresholding with EMD for speech enhancement,"
    Proc. Int. Workshop on Nonlinear Circuits and Signal Processing, pp.232-235 (2008-3)
  29. M. K. I. Molla, K. Hirose, N. Minematsu, M. K. Hasan,
    "A multiband approach for voiced/unvoiced discrimination of speech signals,"
    Proc. Int. Workshop on Nonlinear Circuits and Signal Processing, pp.323-326 (2008-3)
  30. Q. Sun, K. Hirose, N. Minematsu,
    "Improved tone component prediction of tone nucleus for F0 contour generation of Mandarin speech,"
    Proc. Int. Workshop on Nonlinear Circuits and Signal Processing, pp.112-115 (2008-3)

2008 招待講演

  1. 峯松信明，
    "音声言語運用が要求する認知的能力と音声言語工学が構築した計算論的能力"，
    電子情報通信学会音声研究会，SP2008-84，pp.31-36 (2008-12)
  2. N. Minematsu, D. Saito, and K. Hirose,
    "Experimenal study of structure-to-speech conversion -- an implementation of infant-like vocal imitation --,"
    Proc. Int. Conf. Signal Processing (ICSP), pp.651-654 (2008-10)
  3. N. Minematsu,
    "Speech as timbre-based melody,"
    Seminar talk at Psychoacoustics labolatory of Kyushu University (2008-9)
  4. N. Minematsu,
    "Training of pronunciation as learning of the sound system embedded in the target language,"
    Proc. The 8th Phonetic Conference of China and Int. Symposium on Phonetic Frontiers, CD-ROM (2008-4)
  5. N. Minematsu,
    "Speech as music --Yet another framework for speech recognition,"
    ESF-JSPS Frontier Science Conference Series for Young Researchers -- Experimental Cognitive Robotics -- (2008-3)

2008 研究会論文

  1. 峯松信明，
    "音声言語運用が要求する認知的能力と音声言語工学が構築した計算論的能力"，
    電子情報通信学会音声研究会，SP2008-84，pp.31-36 (2008-12)
  2. X. Ma, N. Minematsu, Y. Qiao, K. Hirose, A. Nemoto, and F. Shi,
    "Dialect-based speaker classification of Chinese using acoustic features invariant with extra-linguistic factors,"
    IEICE Technical Report, SP2008    -109, pp.179-184 (2008-12)
  3. 朝川智，喬宇，峯松信明，広瀬啓吉，
    "音声の構造的表象と判別分析を用いた単語音声認識"
    電子情報通信学会音声研究会，SP2008-113，pp.203-208 (2008-12)
  4. 鈴木雅之，喬宇，峯松信明，
    "アフィン変換不変性を有する局所的特徴量を用いた音声認識"，
    電子情報通信学会音声研究会，SP2008-114，pp.209-214 (2008-12)
  5. 國越晶，喬宇，峯松信明，広瀬啓吉，
    "空間写像に基づく手の動きを入力とした音声生成系の構築"，
    電子情報通信学会音声研究会，SP2008-78，pp.45-50 (2008-11)
  6. 松浦良，齋藤大輔，朝川智，峯松信明，広瀬啓吉，
    "構造表象を用いた音声認識におけるパラメータ共有とその効果"，
    電子情報通信学会音声研究会，SP2008-52，pp.55-60 (2008-7)
  7. 喬宇，峯松信明，
    "変換不変性を有するダイバージェンスとその一般形"，
    電子情報通信学会音声研究会，SP2008-51，pp.49-54 (2008-7)
  8. 齋藤大輔，朝川智，峯松信明，広瀬啓吉，
    "構造的表象からの音声合成とそれに基づく音声模倣に関する検討"
    電子情報通信学会音声研究会，SP2008-40，pp.115-120 (2008-6)
  9. 鈴木雅之，朝川智，喬宇，峯松信明，広瀬啓吉，
    "スペクトル特徴量を用いた音声の構造的表象に関する実験的検討"，
    電子情報通信学会音声研究会，SP2008-32    ，pp.73-78 (2008-6)
  10. 羅徳安，下村直也，峯松信明，山内豊，広瀬啓吉，
    "外国語学習を対象としたシャドーイング音声の自動評定法に関する検討"，
    電子情報通信学会音声研究会，SP2008-29，pp.55-60 (2008-6)
  11. 平野宏子，広瀬啓吉，河合剛，峯松信明，
    "英語・中国語・母語話者の日本語朗読音声のF0に現れる特徴"，
    電子情報通信学会音声研究会，SP2008-27，pp.43-48 (2008-6)
  12. Y. Qiao and N. Minematsu,
    "Unsupervised phoneme segmentation using Mahalanobis distance,"
    IEICE Technical Report, SP2007-198, pp.69-74 (2008-3)
  13. 下村直也，峯松信明，山内豊，広瀬啓吉，
    "ボトムアップクラスタリングを用いたシャドーイング音声の自動評定"，
    電子情報通信学会音声研究会，SP2007-212，pp.151-156 (2008-3)

2008 全国大会論文

  1. Y. Qiao and N. Minematsu,
    "Structural representation with a general form of invariant divergence,"
    Proc. Autumn Meeting of Acoust. Soc. Jpn., 2-P-1, pp.105-108 (2008-9)
  2. Y. Qiao, S. Asakawa, N. Minematsu, and K. Hirose,
    "Dimension reduction and discriminant analysis for Japanese connected vowel recognition,"
    Proc. Autumn Meeting of Acoust. Soc. Jpn., 2-P-2, pp.109-112 (2008-9)
  3. 朝川智，喬宇，峯松信明，広瀬啓吉，
    "判別分析と構造構造表象を用いた話者の多様性に超頑健な音声認識"，
    日本音響学会秋季講演論文集，2-P-3，pp.113-116 (2008-9)
  4. 松浦良，齋藤大輔，朝川智，峯松信明，広瀬啓吉，
    "音声の構造的表象を用いた音声認識におけるパラメータ共有に関する考察"，
    日本音響学会秋季講演論文集，2-P-4，pp.117-120 (2008-9)
  5. 齋藤大輔，鎌田敏明，峯松信明，広瀬啓吉，長内隆，蒔苗久則，
    "ケプストラムの回転性とそれに基づく話者認識に関する実験的検討"，
    日本音響学会秋季講演論文集，3-Q-17，pp.189-192 (2008-9)
  6. X. Ma, M. Takazawa, N. Minematsu, and K. Hirose,
    "Chinese dialect classification using acoustic universal structure in speech,"
    Proc. Autumn Meeting of Acoust. Soc. Jpn., 2-P-22, pp.405-408 (2008-9)
  7. 齋藤大輔，峯松信明，広瀬啓吉，
    "ケプストラムの幾何学的特性に着眼した声質変換に関する実験的検討"，
    日本音響学会秋季講演論文集，1-Q-27，pp.385-388 (2008-9)
  8. 國越晶，喬宇，峯松信明，広瀬啓吉，
    "空間写像に基づく手の動きを入力とした音声生成系"，
    日本音響学会秋季講演論文集，1-Q-23，pp.375-376 (2008-9)
  9. 鈴木雅之，朝川智，喬宇，峯松信明，広瀬啓吉，
    "スペクトル領域特徴量を用いた音声の構造的表象による音声認識"，
    日本音響学会秋季講演論文集，1-R-26，pp.473-476 (2008-9)
  10. 羅徳安，下村直也，峯松信明，山内豊，広瀬啓吉，
    "シャドーイング訓練法における外国語学習者の発音分析とその自動評価"，
    日本音響学会秋季講演論文集，1-R-31，pp.485-488 (2008-9)
  11. 細田聖人，広瀬啓吉，峯松信明，
    "話し言葉認識における文節境界情報を用いた言語モデルに関する検討"，
    日本音響学会秋季講演論文集，3-1-8，pp.95-96 (2008-9)
  12. 平野宏子，広瀬啓吉，河合剛，峯松信明，
    "    日本語母語話者と学習者の文発話の基本周波数パターン〜中国語話者・英語話者の日本語と母語の観察から〜"，
    日本音響学会秋季講演論文集，1-Q-2，pp.321-322 (2008-9)
  13. M. Ma, H. Hirano, K. Hirose, and N. Minematsu,
    "Proposal of adaptive CALL system for Japanese learners of Mandarin,"
    Proc. Autumn Meeting of Acoust. Soc. Jpn., 1-Q-6, pp.333-334 (2008-9)
  14. 齋藤大輔，朝川智，峯松信明，西村多寿子，広瀬啓吉，
    "音声の不変表象に基づく語ゲシュタルトの物理的解釈とそれに基づく幼児の音声模倣の実装"，
    人工知能学会全国大会講演論文集，3F3-5，pp.1-4 (2008-6)
  15. 桜庭京子，峯松信明，廣瀬啓吉，田山二朗，今泉敏，山内俊雄，
    "MtFのボイスセラピーにおける成功症例の型の分類"，
    性同一性障害学会研究大会 (2008-3)
  16. 印南圭祐，渡辺美知子，峯松信明，広瀬啓吉，
    "CRFに基づくアクセント変形予測モデルにおけるエラー解析"，
    言語処理学会年次大会発表論文集，pp.969-972 (2008-3)
  17. 鎌田圭，高澤真章，竹内京子，朝川智，峯松信明，牧野武彦，広瀬啓吉，
    "大規模英語学習者を対象とした音声の構造的表象に基づく発音分類とその応用"，
    情報処理学会全国大会講演集，2ZL-6，pp.275-276 (2008-3)
  18. 稲垣貴彦，広瀬啓吉，峯松信明，
    "話し言葉音声認識における韻律的特徴を利用したフィラー検出"，
    日本音響学会春季講演論文集，3-10-20，pp.133-134 (2008-3)
  19. 下村直也，峯松信明，山内豊，喬宇，朝川智，広瀬啓吉，
    "教師無しセグメンテーションを用いたシャドーイング音声の自動評価に関する実験的検討"，
    日本音響学会春季講演論文集，3-10-10，pp.483-486 (2008-3)
  20. 印南圭祐，渡辺美知子，峯松信明，広瀬啓吉，
    "CRFを用いたアクセント結合処理に対する誤り分析とその改良に向けた考察"，
    日本音響学会春季講演論文集，3-Q-18，pp.413-414 (2008-3)
  21. 鎌田圭，高澤真章，朝川智，峯松信明，牧野武彦，広瀬啓吉，
    "音声の構造的表象に基づく英語発音分析結果の視覚化に対する一考察"，
    日本音響学会春季講演論文集，3-Q-23，pp.425-426 (2008-3)
  22. 齋藤大輔，松浦良，鎌田敏明，朝川智，峯松信明，広瀬啓吉，
    "ケプストラムの声道長依存性に対する定量的分析とその応用"，
    日本音響学会春季講演論文集，1-Q-19，pp.201-204 (2008-3)
  23. 齋藤大輔，朝川智，峯松信明，広瀬啓吉，
    "構造的表象からの音声合成における音響空間探索の高速化"，
    日本音響学会春季講演論文集，3-Q-16，pp.407-410 (2008-3)
  24. A. Rebordao, M. K. Islam Molla, K. Hirose, N. Minematsu,
    "A speech denoising system based on ICA and voice activity detection,"
    Proc. Spring Meeting of Acoust. Soc. Japan, 3-Q-7, pp.389-390 (2008-3)
  25. 越智景子，広瀬啓吉，峯松信明，
    "基本周波数パターン生成過程モデルに基づくコーパスベース韻律制御における焦点制御"，
    日本音響学会春季講演論文集，2-11-14，pp.369-370 (2008-3)
  26. 孫慶華，広瀬啓吉，峯松信明，
    "標準中国語音声合成システムの構築"，
    日本音響学会春季講演論文集，3-Q-13，pp.401-402 (2008-3)
  27. 竹内京子，齋藤大輔，峯松信明，広瀬啓吉，
    "フランス語鼻母音のカテゴリー知覚の考察"，
    日本音響学会春季講演論文集，3-7-2，pp.501-502 (2008-3)
  28. 高澤真章，鎌田圭，竹内京子，朝川智，峯松信明，牧野武彦，広瀬啓吉，
    "大規模英語学習者を対象とした音声の構造的表象に基づく発音評価とその応用"，
    日本音響学会春季講演論文集，3-10-12，pp.489-492 (2008-3)
  29. Y. Qiao, N. Shimomura, N. Minematsu,
    "Unsupervised phoneme segmentation using transformed cepstrum features,"
    Proc. Spring Meeting of Acoust. Soc. Japan, 1-11-20, pp.287-290 (2008-3)
  30. アリ・ナジャンド，廣瀬啓吉，峯松信明，
    "文節境界を利用した統計的言語モデルの話し言葉コーパスへの適用"，
    日本音響学会春季講演論文集，3-10-17，pp.125-126 (2008-3)
  31. Juan Pablo Narino M, K. Hirose, N. Minematsu,
    "Improvements to acoustic modeling using Hidden Conditional Random Fields for automatic speech recognition,    "
    Proc. Spring Meeting of Acoust. Soc. Japan, 2-10-3, pp.71-72 (2008-3)