* 発表論文 - 2017 [#v21c7b28]
#contents
** 論文誌 [#k9e28fea]
+ Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Simultaneous optimization of multiple tree-based factor analyzed HMM for speech synthesis,'' IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 25, no. 9, pp. 1532-1541, September, 2017. (Full paper peer reviewed)
&publication(2017/20170628_Journal_IEEE_Takenori_Yoshimura_paper.pdf, paper);
[[link>http://ieeexplore.ieee.org/document/7961246/?arnumber=7961246&source=authoralert]]
+ 橋本佳, 高木信二, ``深層学習に基づく統計的音声合成,''日本音響学会誌, vol. 73, no. 1, pp. 55-62, 2017年1月. （解説論文）
//2017年1月1日
// + Kei Hashimoto and Shinji Takaki, ``Statistical parametric speech synthesis based on deep learning,'' The journal of the acoustical society of Japan, vol. 73, no. 1, pp. 55-62, January, 2017. (Review paper)
&publication(2017/20170101_Journal_ASJ_Kei_Hashimoto_paper.pdf, paper);
** 国際会議 [#l4c6e62c]
+ %%%Kei Sawada%%%, Keiichi Tokuda, Simon King, and Alan W Black,
``The Blizzard Machine Learning Challenge 2017,''
2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.331-337, Okinawa, Japan, December, 2017. (Full paper peer reviewed)
&publication(2017/20171218_IConference_ASRU_Kei_Sawada_paper.pdf, paper);
&publication(2017/20171218_IConference_ASRU_Kei_Sawada_slide.pptx, slide);
+ %%%Kei Sawada%%%, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda,
``The NITech text-to-speech system for the Blizzard Challenge 2017,''
Blizzard Challenge 2017 Workshop, Stockholm, Sweden, August, 2017. (Full paper peer reviewed)
&publication(2017/20170825_IConference_Blizzard_Kei_Sawada_paper.pdf, paper);
&publication(2017/20170825_IConference_Blizzard_Kei_Sawada_slide.pptx, slide);
+ %%%Amelia J. Gully%%%, Takenori Yoshimura, Damian T. Murphy, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda,
``Articulatory text-to-speech synthesis using the digital waveguide mesh driven by a deep neural network,'' Interspeech 2017, pp. 234-238, Stockholm, Sweden, August, 2017. (Full paper peer reviewed)
&publication(2017/20170821_IConference_Interspeech_Amelia_Gully_paper.pdf, paper);
+ %%%Yoshinari Tsuzuki%%%, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Image recognition based on discriminative models using features generated from separable lattice HMMs,'' 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.2607-2611, New Orleans, USA, May, 2017.（IEEE名古屋支部優秀学生賞)(Full paper peer reviewed)
&publication(2017/20170308_IConference_ICASSP_Yoshinari_Tsuzuki_paper.pdf, paper);
&publication(2017/20170308_IConference_ICASSP_Yoshinari_Tsuzuki_slide.pdf, poster);
[[link>http://ieee-nagoya.org/]]
** 研究会 [#f92cca8f]
+ 浅見太一, 大谷大和, 岡本拓磨, 小川哲司, 落合翼, 亀岡弘和, 駒谷和範, 高木信二, 高道慎之介, 俵直弘, 南條浩輝, 橋本佳, 福田 隆, 増村亮, 松田繁樹, 李晃伸, 渡部晋治, ``国際会議ICASSP2017報告,'' 音声言語情報処理研究会, vol. 2017-SLP-117, no. 3, pp. 1-8, 2017年7月.
//2017/7/27
&publication(2017/20170217_TReport_SLP_Kei_Hashimoto_paper.pdf, paper);
+ 浅見太一, 小川厚徳, 小川哲司, 大谷大和, 倉田岳人, 齋藤大輔, 塩田さやか, 篠原雄介, 鈴木雅之, 高道慎之介, 南條浩輝, 橋本佳, 樋口卓哉, 増村亮, 吉野幸一郎, 渡部晋治, ``国際会議INTERSPEECH2016報告,'' 音声言語情報処理研究会, vol. 2017-SLP-115, no. 7, pp. 1-7, 2017年2月.
//2017/2/17
&publication(2017/20170217_TReport_SLP_Kei_Hashimoto_paper.pdf, paper);
+ %%%橋本佳%%%, 大浦圭一郎, 南角吉彦, 徳田恵一,``DNN音声合成における音響特徴量系列とその時間構造の同時モデル化,'' 音声研究会, vol. 116, no. 414, SP2016-76, pp. 71-76, 東京, 日本, 2017年1月.（音声研究会研究奨励賞）
// + %%%Kei Hashimoto%%%, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Simultaneous modeling of acoustic feature sequences and its temporal structures for DNN-based speech synthesis,'' SP, vol. 116, no. 414, SP2016-76, pp. 71-76, Tokyo, Japan, January, 2017.
&publication(2017/20170121_TReport_SP_Kei_Hashimoto_paper.pdf, paper);
&publication(2017/20170121_TReport_SP_Kei_Hashimoto_slide.pptx, slide);
[[link>http://www.ieice.org/iss/sp/jpn/special/sp-prize.html]]
[[link>http://www.ieice.org/ken/paper/20170121nbpX/]]
+ %%%浅井千明%%%, 沢田慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一,``オーディオブックを用いた表現豊かな音声合成のための言語特徴の検討,'' 音声研究会, vol. 116, no. 414, SP2016-76, pp. 35-50, 東京, 日本, 2017年1月.
// + %%%Chiaki Asai%%%, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Designing linguistic features for expressive speech sysnthesis using audiobooks,'' SP, vol. 116, no. 414, SP2016-76, pp. 35-40, Tokyo, Japan, January, 2017.
&publication(2017/20170121_TReport_SP_Chiaki_Asai_paper.pdf, paper);
&publication(2017/20170121_TReport_SP_Chiaki_Asai_poster.pdf, poster);
** 全国大会 [#y86c4dc0]
+ %%%沢田慶%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一,
``Blizzard Challenge 2017のためのNITechテキスト音声合成システム,''
日本音響学会2017年秋季研究発表会, pp. 287-290, 愛媛, 日本, 2017年9月.
//%%%Kei Sawada%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Overview of the NITech text-to-speech system for the Blizzard Challenge 2017,'' Acoustical Society of Japan 2017 Autumn Meeting, pp. 287-290, Ehime, Japan, September, 2017.
&publication(2017/20170926_DConference_ASJA_Kei_Sawada_paper.pdf, paper);
&publication(2017/20170926_DConference_ASJA_Kei_Sawada_poster.pptx, poster);
&publication(2017/20170926_DConference_ASJA_Kei_Sawada_abst.pdf, abst);
+ %%%法野行哉%%%, 沢田慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一,
``音楽SNSの投稿データを利用した歌唱声質変換,''
日本音響学会2017年秋季研究発表会, pp. 209-210, 愛媛, 日本, 2017年9月.
//%%%Yukiya Hono%%%, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Singing voice conversion using post data in music SNS.'' Acoustical Society of Japan 2017 Autumn Meeting, pp. 209-210, Ehime, Japan, September, 2017.
&publication(2017/20170925_DConference_ASJA_Yukiya_Hono_paper.pdf, paper);
&publication(2017/20170925_DConference_ASJA_Yukiya_Hono_slide.pptx, slide);
&publication(2017/20170925_DConference_ASJA_Yukiya_Hono_abst.pdf, abst);
+ %%%丹羽純平%%%, 吉村建慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一,
``WaveNet-based voice conversion,''
日本音響学会2017年秋季研究発表会, pp. 207-208, 愛媛, 日本, 2017年9月.
//%%%Jumpei Niwa%%%, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``WaveNet-based voice conversion,'' Acoustical Society of Japan 2017 Autumn Meeting, pp. 207-208, Ehime, Japan, September, 2017.
&publication(2017/20170925_DConference_ASJA_Jumpei_Niwa_paper.pdf, paper);
&publication(2017/20170925_DConference_ASJA_Jumpei_Niwa_slide.pptx, slide);
&publication(2017/20170925_DConference_ASJA_Jumpei_Niwa_abst.pdf, abst);
+ %%%吉村建慶%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一,
``WaveNetにおけるメルケプストラムに基づくノイズシェーピング量子化法の適用,''
日本音響学会2017年秋季研究発表会, pp. 193-194, 愛媛, 日本, 2017年9月.（学生優秀発表賞）
//%%%Takenori Yoshimura%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Mel-cepstrum based quantization noise shaping applied for WaveNet,'' Acoustical Society of Japan 2017 Autumn Meeting, pp. 193-194, Ehime, Japan, September, 2017.
&publication(2017/20170925_DConference_ASJA_Takenori_Yoshimura_paper.pdf, paper);
&publication(2017/20170925_DConference_ASJA_Takenori_Yoshimura_slide.pptx, slide);
&publication(2017/20170925_DConference_ASJA_Takenori_Yoshimura_abst.pdf, abst);
+ %%%市川裕詞%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一,``DNN-GMMハイブリッドモデルに基づく声質変換の検討,'' 日本音響学会2017年春季研究発表会, pp. 233-234, 神奈川, 日本, 2017年3月.（日本音響学会学生優秀発表賞）
// + %%%Yushi Ichikawa%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Voice Conversion Based on Hybrid Deep Neural Network - Gaussian Mixture Model,'' Acoustical Society of Japan 2017 Spring Meeting , pp. 233-234, Kanagawa, Japan, March, 2017.
&publication(2017/20170315_DConference_ASJS_Yushi_Ichikawa_paper.pdf, paper);
&publication(2017/20170315_DConference_ASJS_Yushi_Ichikawa_slide.pptx, slide);
&publication(2017/20170315_DConference_ASJS_Yushi_Ichikawa_abst.pdf, abst);
[[link>http://www.asj.gr.jp/recommending/07_gakusei.html]]
+ %%%村瀬栞%%%, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, ``ニューラルネットワークに基づく音声合成における音響特徴量抽出条件の検討,'' 日本音響学会2017年春季研究発表会, pp. 263-264, 神奈川, 日本, 2017年3月.
// + %%%Shiori Murase%%%, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Investigation of conditions for acoustic feature extraction for speech synthesis based on deep neural networks,'' Acoustical Society of Japan 2017 Spring Meeting , pp. 263-264, Kanagawa, Japan, March, 2017.
&publication(2017/20170316_DConference_ASJS_Shiori_Murase_paper.pdf, paper);
&publication(2017/20170316_DConference_ASJS_Shiori_Murase_abst.pdf, abst);
** 学位論文 [#dfeda659]
+ %%%脇口甲太郎%%%,
``階層識別モデルの音声認識における生成モデルの構造を考慮したニューラルネットワーク,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Kotaro Wakiguchi%%%, ``Neural network considering structures of generative models for speech recognition based on hierarchical discriminative models,,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Kotaro_Wakiguchi_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Kotaro_Wakiguchi_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Kotaro_Wakiguchi_abst.pdf, abst);
+ %%%横田なつみ%%%,
``分離型格子HMMに基づく画像認識における認識対象に適したモデル構造の調査,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Natsumi Yokota%%%, ``Investigation of model structures suitable for recognized objects in image recognition based on separable lattice hmms,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Natsumi_Yokota_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Natsumi_Yokota_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Natsumi_Yokota_abst.pdf, abst);
+ %%%村瀬栞%%%,
``DNN音声合成における音響特徴量抽出のための最適パラメータの検討,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Shiori Murase%%%, ``The optimal parameter of acoustic feature extraction for speech synthesis based on deep neural network,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Shiori_Murase_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Shiori_Murase_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Shiori_Murase_abst.pdf, abst);
+ %%%法野行哉%%%,
``生成モデルの構造を利用したディープニューラルネットワークに基づく歌声合成,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Yukiya Hono%%%, ``Singing voice synthesis based on deep neural networks using generative model structures,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Yukiya_Hono_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Yukiya_Hono_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Yukiya_Hono_abst.pdf, abst);
+ %%%丹羽純平%%%,
``ディープニューラルネットワークに基づく声質変換における入出力特徴量の検討,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Jumpei Niwa%%%, ``Input and output features for deep neural network based voice conversion,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Jumpei_Niwa_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Jumpei_Niwa_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Jumpei_Niwa_abst.pdf, abst);
+ %%%小池なつみ%%%,
``話者認識のための特徴抽出からクラス識別までを統合した単一統計モデル,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Natsumi Koike%%%, ``A single statistical model integrating feature extraction and class identification for speaker recognition,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Natsumi_Koike_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Natsumi_Koike_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Natsumi_Koike_abst.pdf, abst);
+ %%%市橋史也%%%,
``音声認識における音響モデルとデコーディングパラメータが与える影響の調査,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Fumiya_Ichihashi%%%, ``Investigation of effect by acoustic models and decording parameters in speech recognition,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Fumiya_Ichihashi_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Fumiya_Ichihashi_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Fumiya_Ichihashi_abst.pdf, abst);
+ %%%市川英嗣%%%,
``ディープニューラルネットワークを出力確率分布に用いた分離型格子HMMに基づく画像認識,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Eiji Ichikawa%%%, ``Image recognition based on separable lattice hmms using a deep neural network for output probability distributions,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Eiji_Ichikawa_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Eiji_Ichikawa_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Eiji_Ichikawa_abst.pdf, abst);
+ %%%池浦史芳%%%,
``雑音環境下における感情合成音声の聞き取りやすさと親しみやすさの評価,''
卒業論文, 名古屋工業大学, 2017年2月.
//%%%Fumiyoshi Ikeura%%%, ``Evaluations of intelligibility and familiarity of synthesized emotional speech under noisy environments,'' Bachelor thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170213_Thesis_Bachelor_Fumiyoshi_Ikeura_paper.pdf, paper);
&publication(2017/20170213_Thesis_Bachelor_Fumiyoshi_Ikeura_slide.pptx, slide);
&publication(2017/20170213_Thesis_Bachelor_Fumiyoshi_Ikeura_abst.pdf, abst);
+ %%%水谷友哉%%%,
``因子分析に基づく構造化事前分布を用いた変分ベイズ法による声質変換,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Tomoya Mizutani%%%, ``Voice conversion based on a variational bayesian method using prior distribution structured with factor analysis,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Tomoya_Mizutani_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Tomoya_Mizutani_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Tomoya_Mizutani_abst.pdf, abst);
+ %%%肥田裕弘%%%,
``重み付き有限状態トランスデューサに基づく階層型音声認識デコーダの開発,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Masahiro Hida%%%, ``Development of a hierarchical speech recognition decoder based on weighted finite-state transducers,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Masahiro_Hida_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Masahiro_Hida_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Masahiro_Hida_abst.pdf, abst);
+ %%%橋本聖矢%%%,
``複数音響特徴量の生成モデルによる特徴量を用いた識別モデルに基づく話者認識,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Masaya Hashimoto%%%, ``Speaker recognition based on discriminative models using features generated from statistical generative models with multiple acoustic features,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Masaya_Hashimoto_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Masaya_Hashimoto_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Masaya_Hashimoto_abst.pdf, abst);
+ %%%鹿野本気%%%,
``可変長フレームと波形の直接モデル化に基づくHMM音声合成の検討,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Motoki Shikano%%%, ``Hmm-based speech synthesis based on direct speech waveform modelling with variable length frames,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Motoki_Shikano_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Motoki_Shikano_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Motoki_Shikano_abst.pdf, abst);
+ %%%梅村真由%%%,
``DNN歌声合成における楽譜と発声のずれを考慮した学習法,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Chiaki Asai%%%, ``Dnn-based singing voice synthesis considering time lags between musical scores and singer's vocals,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Mayu_Umemura_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Mayu_Umemura_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Mayu_Umemura_abst.pdf, abst);
+ %%%市川裕詞%%%,
``DNN-GMMハイブリッドモデルに基づいた声質変換,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Yushi Ichikawa%%%, ``Hybrid deep neural network - gaussian mixture model based voice conversion,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Yushi_Ichikawa_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Yushi_Ichikawa_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Yushi_Ichikawa_abst.pdf, abst);
+ %%%安藤雄輝%%%,
``大語彙連続音声認識における統計モデルに基づく識別的な仮説の枝刈り,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Yuki Ando%%%, ``Discriminative hypothesis pruning based on statistical models in large vocabulary continuous speech recognition,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Yuki_Ando_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Yuki_Ando_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Yuki_Ando_abst.pdf, abst);
+ %%%浅井千明%%%,
``オーディオブックを用いた表現豊かな音声合成のための言語特徴の設計,''
修士論文, 名古屋工業大学, 2017年2月.
//%%%Chiaki Asai%%%, ``Linguistic feature design for expressive speech synthesis using audiobooks,'' Master thesis, Nagoya institute of technology, February, 2017.
&publication(2017/20170210_Thesis_Master_Chiaki_Asai_paper.pdf, paper);
&publication(2017/20170210_Thesis_Master_Chiaki_Asai_slide.pptx, slide);
&publication(2017/20170210_Thesis_Master_Chiaki_Asai_abst.pdf, abst);
** 著書 [#qc61df3e]
+ 橋本佳（分担執筆）, ``人工知能学大辞典（音声合成（HMM 合成方式））,'' 人工知能学会編, 共立出版, pp.785-787, 2017年7月.
//2017年7月7日
+ Keiichi Tokuda, Akinobu Lee, Yoshihiko Nankaku, Keiichiro Oura, Kei Hashimoto, Daisuke Yamamoto, Ichi Takumi, Takahiro Uchiya, Shuhei Tsutsumi, Steve Renals, and Junichi Yamagishi（分担執筆）, ``Human harmonized information technology Volume2,'' Computer Science keyword, Springer press, pp. 77-114, May, 2017.
&publication(2017/20170505_Sringer_Keiichi_Tokuda_book.pdf, book);
//2017/05/05
+ 橋本佳（分担執筆）, ``音響学入門ペディア（統計的音声合成の仕組みを教えてください）,'' 日本音響学会編, コロナ社, 2017年3月.
//2017年3月15日
** 記事 [#ka7ac954]
+ 徳田恵一, ``風雲急を告げる音声合成研究の最新動向,'' 電子情報通信学会情報・システムソサイエティ誌, vol. 21, no. 4, pp. 10-11, 2017年2月.
//2017年2月1日
&publication(2017/20170201_Journal_IEICEISS_Keiichi_Tokuda_paper.pdf, paper);
** 講演 [#z5a36a58]
+ 橋本佳, ``音声合成における深層学習,'' 日本音響学会2017年秋季研究発表会ビギナーズセミナー, 愛媛, 日本, 2017年9月.
//2017年9月25日
&publication(2017/20170925_DConference_ASJA_Kei_Hashimoto_slide.pptx, slide);
**過去の発表論文 [#q989580e]
#ls2(ホーム/発表論文/,reverse);
