Publications | Takamichi Lab. / 高道研究室

2024

Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data

Hitoshi Suda , Aya Watanabe , and Shinnosuke Takamichi

In Proceedings of Interspeech , 2024

@inproceedings{suda24interspeech_sukikirai,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data},
  author = {Suda, Hitoshi and Watanabe, Aya and Takamichi, Shinnosuke},
  year = {2024},
  memo = {This work was supported by JSPS KAKENHI Grant Number 23K20017, 21H04900, 22H03639, and 23H03418, and JST FOREST JPMJFR226V. This paper is based on results obtained from a project, JPNP20006, commissioned by the New Energy and Industrial Technology Development Organization (NEDO).}
}

コーパス

SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark

Yuki Saito , Takuto Igarashi , Kentaro Seki , and 4 more authors

In Proceedings of Interspeech , 2024

Bib

@inproceedings{saito24interspeech_src4vc,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark},
  author = {Saito, Yuki and Igarashi, Takuto and Seki, Kentaro and Takamichi, Shinnosuke and Yamamoto, Ryuichi and Tachibana, Kentaro and Saruwatari, Hiroshi},
  year = {2024},
  memo = {This research was conducted as joint research between LY Corporation and Saruwatari-Takamichi Laboratory of The University of Tokyo, Japan. This work was supported by Research Grant S of the Tateishi Science and Technology Foundation.}
}

Textless Dependency Parsing by Labeled Sequence Prediction

Shunsuke Kando , Yusuke Miyao , Jason Naradowsky , and 1 more author

In Proceedings of Interspeech , 2024

Bib

@inproceedings{kando24interspeech_textlessparsing,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {Textless Dependency Parsing by Labeled Sequence Prediction},
  author = {Kando, Shunsuke and Miyao, Yusuke and Naradowsky, Jason and Takamichi, Shinnosuke},
  year = {2024},
  memo = {This work was supported by JST Moonshot JPMJMS2237 and
  JST FOREST JPMJFR226V.}
}

音声変換

Noise-Robust Voice Conversion by Conditional Denoising Training Using Latent Variables of Recording Quality and Environment

Takuto Igarashi , Yuki Saito , Kentaro Seki , and 3 more authors

In Proceedings of Interspeech , 2024

Bib

@inproceedings{igarashi24interspeech_noise-robust-vc,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {Noise-Robust Voice Conversion by Conditional Denoising Training Using Latent Variables of Recording Quality and Environment},
  author = {Igarashi, Takuto and Saito, Yuki and Seki, Kentaro and Takamichi, Shinnosuke and Yamamoto, Ryuichi and Saruwatari, Kentaro Tachibanaand Hiroshi},
  year = {2024}
}

音声変換

Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals

Kentaro Seki , Shinnosuke Takamichi , Norihiro Takamune , and 3 more authors

In Proceedings of Interspeech , 2024

Bib

@inproceedings{seki24interspeech_spatial-voice-conversion,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals},
  author = {Seki, Kentaro and Takamichi, Shinnosuke and Takamune, Norihiro and Saito, Yuki and Imamura, Kanami and Saruwatari, Hiroshi},
  year = {2024},
  memo = {This work is supported by Research Grant S of the Tateishi Science and Technology Foundation.}
}

speechevaluation

SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics

Takaaki Saeki , Soumi Maiti , Shinnosuke Takamichi , and 2 more authors

In Proceedings of Interspeech , 2024

Bib

@inproceedings{saeki24interspeech_speechbertscore,
  abbr = speechevaluation,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics},
  author = {Saeki, Takaaki and Maiti, Soumi and Takamichi, Shinnosuke and Watanabe, Shinji and Saruwatari, Hiroshi},
  year = {2024},
  memo = {JSPS 科 研 費 23H03418，23K18474，22H03639，21H05054，22KJ0838 ムーンショット研究開発費 JPMJPS2011，および JST FOREST JPMJFR226V によって支援された．}
}

コーパス

SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis

Osamu Take , Shinnosuke Takamichi , Kentaro Seki , and 2 more authors

In Proceedings of Interspeech , 2024

Bib

@inproceedings{take24interspeech_saslaw,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis},
  author = {Take, Osamu and Takamichi, Shinnosuke and Seki, Kentaro and Bando, Yoshiaki and Saruwatari, Hiroshi},
  year = {2024},
  memo = {Part of this work was supported by JSPS KAKENHI Grant
  Number 23H03418 and 22H03639, Moonshot R&D Grant Number JPMJPS2011, and JST FOREST JPMJFR226V. The authors also thank Aya Watanabe for her support in designing the figures for this paper.}
}

音響合成

環境音の模倣音声を利用した環境音合成とデータセット構築

岡本悠希 , 井本桂右 , 高道慎之介 , and 3 more authors

In 電子情報通信学会応用音響研究会 , 2024

Bib PDF

@inproceedings{okamoto24ea_voice-to-foley,
  abbr_publisher = {電子情報通信学会 応用音響研究会},
  booktitle = {電子情報通信学会 応用音響研究会},
  title = {環境音の模倣音声を利用した環境音合成とデータセット構築},
  author = {悠希, 岡本 and 桂右, 井本 and 慎之介, 高道 and 亮太郎, 永瀬 and 隆寛, 福森 and 洋一, 山下},
  year = {2024},
}

コーパス

音声の生成ＡＩが拓く未来

高道慎之介

電気三学会関西支部専門講習会, 2024

(Invited talk / 招待講演)

Bib

@article{takamichi24denki_invited-talk,
  title = {音声の生成ＡＩが拓く未来},
  author = {慎之介, 高道},
  year = {2024},
  journal = {電気三学会関西支部専門講習会},
  note = {(Invited talk / 招待講演)}
}

楽音合成

Audio Effect Chain Estimation and Dry Signal Recovery from Multi-Effect-Processed Musical Signals

Osamu Take , Kento Watanabe , Takayuki Nakatsuka , and 5 more authors

In Proceedings of International Conference on Digital Audio Effects (DAFx) , 2024

Bib

@inproceedings{take24dafx_effect-chain,
  abbr_publisher = {Proceedings of International Conference on Digital Audio Effects (DAFx)},
  booktitle = {Proceedings of International Conference on Digital Audio Effects (DAFx)},
  title = {Audio Effect Chain Estimation and Dry Signal Recovery from Multi-Effect-Processed Musical Signals},
  author = {Take, Osamu and Watanabe, Kento and Nakatsuka, Takayuki and Cheng, Tian and Nakano, Tomoyasu and Goto, Masataka and Takamichi, Shinnosuke and Saruwatari, Hiroshi},
  memo = {This work is supported by JSPS KAKENHI 21H04900,
  22H03639, and 23H03418, JST FOREST JPMJFR226V, and
  Moonshot R&D Grant Number JPMJPS2011.},
  year = {2024}
}

コーパス

JVNV: A Corpus of Japanese Emotional Speech with Verbal Content and Nonverbal Expressions

Detai Xin , Junfeng Jiang , Shinnosuke Takamichi , and 3 more authors

IEEE Access, 2024

arXiv Bib Website

@article{xin24access_jvnv-corpus,
  title = {{JVNV}: A Corpus of Japanese Emotional Speech with Verbal Content and Nonverbal Expressions},
  author = {Xin, Detai and Jiang, Junfeng and Takamichi, Shinnosuke and Saito, Yuki and Aizawa, Akiko and Saruwatari, Hiroshi},
  year = {2024},
  journal = {IEEE Access},
}

コーパス

JNV Corpus: A Corpus of Japanese Nonverbal Vocalizations with Diverse Phrases and Emotions

Detai Xin , Shinnosuke Takamichi , and Hiroshi Saruwatari

Speech Communication, 2024

arXiv Bib Website

@article{xin24specom_jnv-corpus,
  title = {{JNV} Corpus: A Corpus of Japanese Nonverbal Vocalizations with Diverse Phrases and Emotions},
  author = {Xin, Detai and Takamichi, Shinnosuke and Saruwatari, Hiroshi},
  year = {2024},
  journal = {Speech Communication},
}

音声合成

Text-Inductive Graphone-Based Language Adaptation for Low-Resource Speech Synthesis

Takaaki Saeki , Soumi Maiti , Xinjian Li , and 3 more authors

IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024

Bib Code

@article{saeki24taslp_text-inductive-tts,
  title = {Text-Inductive Graphone-Based Language Adaptation for Low-Resource Speech Synthesis},
  author = {Saeki, Takaaki and Maiti, Soumi and Li, Xinjian and Watanabe, Shinji and Takamichi, Shinnosuke and Saruwatari, Hiroshi},
  year = {2024},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing}
}

音声復元

SelfRemaster: Self-Supervised Speech Restoration for Historical Audio Resources

Takaaki Saeki , Shinnosuke Takamichi , Tomohiko Nakamura , and 2 more authors

IEEE Access, 2024

arXiv Bib HTML Code Website

@article{saeki24access_selfremaster,
  title = {{SelfRemaster}: Self-Supervised Speech Restoration for Historical Audio Resources},
  author = {Saeki, Takaaki and Takamichi, Shinnosuke and Nakamura, Tomohiko and Tanji, Naoko and Saruwatari, Hiroshi},
  year = {2024},
  journal = {IEEE Access},
}

音声合成

Emotion-controllable Speech Synthesis using Emotion Soft Label, Utterance-level Prosodic Factors, and Word-level Prominence

Xuan Luo , Shinnosuke Takamichi , Yuki Saito , and 2 more authors

APSIPA Transactions, 2024

Bib PDF

@article{luo24apsipa-trans_emotion-synthesis,
  title = {Emotion-controllable Speech Synthesis using Emotion Soft Label, Utterance-level Prosodic Factors, and Word-level Prominence},
  author = {Luo, Xuan and Takamichi, Shinnosuke and Saito, Yuki and Koriyama, Tomoki and Saruwatari, Hiroshi},
  year = {2024},
  journal = {APSIPA Transactions},
}

コーパス

インターネット時代の音声コーパスの作成

高道慎之介

日本音響学会誌, 2024

(Invited article / 招待記事)

Bib PDF

@article{takamichi24asj_invited-article-dark-data,
  title = {インターネット時代の音声コーパスの作成},
  author = {慎之介, 高道},
  year = {2024},
  journal = {日本音響学会誌},
  note = {(Invited article / 招待記事)},
  memo = {本研究は科研費 21H04900，22H03639，23H03418，23K18474，JST創発的研究支援事業 JP23KJ0828，ムーンショット JPMJPS2011 の助成を受けた．また，本稿の執筆にあたり東京大学 大学院情報理工学系研究科 修士課程 関 健太郎氏からの助言を受けた．}
}

コーパス

環境音に対する日本語自由記述文コーパスとベンチマーク分析

岡本悠希 , 高道慎之介 , 森松亜依 , and 3 more authors

In 言語処理学会全国大会 , 2024

Bib PDF

@inproceedings{okamoto24nlp_multi-lingual-audiocaps,
  abbr_publisher = {言語処理学会 全国大会},
  booktitle = {言語処理学会 全国大会},
  title = {環境音に対する日本語自由記述文コーパスとベンチマーク分析},
  author = {悠希, 岡本 and 慎之介, 高道 and 亜依, 森松 and 亞椰, 渡邊 and 桂右, 井本 and 洋一, 山下},
  year = {2024},
  memo = {本研究は，ムーンショット JPMJPS2011，JST 創発的研 究支援事業 JP23KJ0828，科研費 21H05054，21H04900，22H0363， 23H03418，23K16908 の支援を受け実施した.}
}

歌声合成

歌唱者間相互作用を再現するDNN重唱歌声合成の検討

兵藤弘明 , 高道慎之介 , 中村友彦 , and 2 more authors

In 情報処理学会音楽情報科学研究会 , 2024

Bib PDF

@inproceedings{hyodo24mus_chorus-synthesis,
  abbr_publisher = {情報処理学会 音楽情報科学研究会},
  booktitle = {情報処理学会 音楽情報科学研究会},
  title = {歌唱者間相互作用を再現する{DNN}重唱歌声合成の検討},
  author = {弘明, 兵藤 and 慎之介, 高道 and 友彦, 中村 and 純矢, 小口 and 洋, 猿渡},
  year = {2024},
  memo = {アノテーションの方法について，西山陽子様から 多くの助言を受けた．本研究は JST 創発的研究支援事業 JPMJFR226V，JSPS 科研費 23H03418，23K18474 の助成を受けた．}
}

音声評価

テキスト生成の自動評価尺度に基づく音声生成の自動評価

佐伯高明 , マイティソウミ , 高道慎之介 , and 2 more authors

In 電子情報通信学会音声研究会 , 2024

Bib PDF

@inproceedings{saeki24sp_speechevaluation,
  abbr_publisher = {電子情報通信学会 音声研究会},
  booktitle = {電子情報通信学会 音声研究会},
  title = {テキスト生成の自動評価尺度に基づく音声生成の自動評価},
  author = {高明, 佐伯 and ソウミ, マイティ and 慎之介, 高道 and 晋治, 渡部 and 洋, 猿渡},
  year = {2024},
  memo = {JSPS 科 研 費 23H03418，23K18474，22H03639，21H05054，22KJ0838 ムーンショット研究開発費 JPMJPS2011，および JST FOREST JPMJFR226V によって支援された．}
}

コーパス

SRC4VCデータセット：多話者音声変換モデルのベンチマークを目的とした実デバイス収録音声コーパス

齋藤佑樹 , 五十嵐琢斗 , 関健太郎 , and 4 more authors

In 電子情報通信学会音声研究会 , 2024

Bib

@inproceedings{saito24sp_real-environment-vc,
  abbr_publisher = {電子情報通信学会 音声研究会},
  booktitle = {電子情報通信学会 音声研究会},
  title = {{SRC4VC}データセット：多話者音声変換モデルのベンチマークを目的とした実デバイス収録音声コーパス},
  author = {佑樹, 齋藤 and 琢斗, 五十嵐 and 健太郎, 関 and 慎之介, 高道 and 龍一, 山本 and 健太郎, 橘 and 洋, 猿渡},
  year = {2024},
  memo = {This research was conducted as joint research between LY Corporation and Saruwatari-Takamichi Laboratory of The University of Tokyo, Japan. This work was supported by Research Grant S of the Tateishi Science and Technology Foundation.}
}

コーパス

音環境に適応するテキスト音声合成のための一人称視点コーパス構築

武伯寒 , 高道慎之介 , 関健太郎 , and 2 more authors

In 情報処理学会音声言語処理研究会 , 2024

Bib PDF

@inproceedings{take24slp_1st-person-tts,
  abbr_publisher = {情報処理学会 音声言語処理研究会},
  booktitle = {情報処理学会 音声言語処理研究会},
  title = {音環境に適応するテキスト音声合成のための一人称視点コーパス構築},
  author = {伯寒, 武 and 慎之介, 高道 and 健太郎, 関 and 宜昭, 坂東 and 洋, 猿渡},
  year = {2024},
  memo = {本研究の一部は，科研費 22H03639，23K18474， JST 創発的研究支援事業 JP23KJ0828，及び JST ムーンショット型研究開発事業 JPMJMS2011 の助成を受け実施 しました．また, 原稿の作成に際して, 渡邊 亞椰さんには 図の作成でご協力頂きました. この場を借りて感謝申し上げます}
}

コーパス

「キミは私の声、好きかな?」大規模主観評価による声質好感度コーパスの構築とその分析

須田仁志 , 渡邊亞椰 , and 高道慎之介

In 情報処理学会音声言語処理研究会 , 2024

Bib PDF

@inproceedings{suda24slp_voice-attractiveness,
  abbr_publisher = {情報処理学会 音声言語処理研究会},
  booktitle = {情報処理学会 音声言語処理研究会},
  title = {「キミは私の声、好きかな?」大規模主観評価による声質好感度コーパスの構築とその分析},
  author = {仁志, 須田 and 亞椰, 渡邊 and 慎之介, 高道},
  year = {2024},
  memo = {本研究は JSPS 科研費 23K20017，21H04900， 22H03639，23H03418，JST 創発的研究支援事業 JPMJFR226V の助成を受けたものです．この成果は，国立研 究開発法人新エネルギー・産業技術総合開発機構（NEDO） の委託業務（JPNP20006）の結果得られたものです．}
}

コーパス

J-SpAW:話者照合となりすまし検出のための日本語音声コーパス

菅野滉大 , 高道慎之介 , and 塩田さやか

In 情報処理学会音声言語処理研究会 , 2024

Bib PDF

@inproceedings{kanno24slp_j-spaw,
  abbr_publisher = {情報処理学会 音声言語処理研究会},
  booktitle = {情報処理学会 音声言語処理研究会},
  title = {{J-SpAW}:話者照合となりすまし検出のための日本語音声コーパス},
  author = {滉大, 菅野 and 慎之介, 高道 and さやか, 塩田},
  year = {2024},
  memo = {本研究は JSPS 科研費 JP24K14993, 22H03639 の助成を受けたものです．}
}

音声変換

音声品質と音響環境の潜在変数で条件付けたDenoising Trainingによるノイズロバスト音声変換

五十嵐琢斗 , 齋藤佑樹 , 関健太郎 , and 4 more authors

In 電子情報通信学会音声研究会 , 2024

Bib PDF

@inproceedings{igarashi24sp_denosing-training-vc,
  abbr_publisher = {電子情報通信学会 音声研究会},
  booktitle = {電子情報通信学会 音声研究会},
  title = {音声品質と音響環境の潜在変数で条件付けたDenoising Trainingによるノイズロバスト音声変換},
  author = {琢斗, 五十嵐 and 佑樹, 齋藤 and 健太郎, 関 and 慎之介, 高道 and 龍一, 山本 and 健太郎, 橘 and 洋, 猿渡},
  year = {2024},
}

音声合成

大規模な日本語笑い声コーパスを用いたテキストレス笑い声合成

辛徳泰 , 高道慎之介 , 森松亜依 , and 1 more author

In 日本音響学会春季研究発表会 , 2024

Bib PDF

@inproceedings{xin24asjs_laughter-synthesis,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {大規模な日本語笑い声コーパスを用いたテキストレス笑い声合成},
  author = {徳泰, 辛 and 慎之介, 高道 and 亜依, 森松 and 洋, 猿渡},
  year = {2024},
  memo = {本研究は，JST 次世代研究者挑戦的研究プログラム JPMJSP2108，JSPS 科研費 JP23KJ0828，JST 創発的研究支援事業 JPMJFR22 の支援を受けたものです。}
}

楽音合成

複数のオーディオエフェクトが適用された楽音に対するエフェクトチェイン推定と原音復元

武伯寒 , 渡邉研斗 , 中塚貴之 , and 5 more authors

In 日本音響学会春季研究発表会 , 2024

Bib PDF

@inproceedings{take24asjs_audio-effect,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {複数のオーディオエフェクトが適用された楽音に対するエフェクトチェイン推定と原音復元},
  author = {伯寒, 武 and 研斗, 渡邉 and 貴之, 中塚 and Cheng, Tian and 倫靖, 中野 and 真孝, 後藤 and 慎之介, 高道 and 洋, 猿渡},
  year = {2024},
  memo = {本研究は科研費 21H04900, 22H03639，23H03418， JST 創発的研究支援事業 JP23KJ0828，ムーンショット JPMJPS2011 の助成を受けたものです}
}

音声合成

日本語音声合成における対話行為情報の利用による韻律改善

佐藤匡紀 , 高道慎之介 , and 猿渡洋

In 日本音響学会春季研究発表会 , 2024

Bib PDF

@inproceedings{sato24asjs_dialogue-context,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {日本語音声合成における対話行為情報の利用による韻律改善},
  author = {匡紀, 佐藤 and 慎之介, 高道 and 洋, 猿渡},
  year = {2024},
  memo = {本研究の一部は，JSPS 科研費 21H04900 と 21H05054 の助成の委託を受け実施した．}
}

音声認識

Cocktail Machine Speech Chain: 重複あり音声を用いた音声認識・音声合成モデルの統一的学習

松永裕太 , 高道慎之介 , 上乃聖 , and 1 more author

In 日本音響学会春季研究発表会 , 2024

Bib PDF

@inproceedings{matsunaga24asjs_cocktail-speech-chain,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {Cocktail Machine Speech Chain: 重複あり音声を用いた音声認識・音声合成モデルの統一的学習 },
  author = {裕太, 松永 and 慎之介, 高道 and 聖, 上乃 and 洋, 猿渡},
  year = {2024},
  memo = {本研究は，JST 次世代研究者挑戦的研究プログラム JPMJSP2108，ムーンショット JPMJPS2011，JST 創発的研究支 援事業 JP23KJ0828，科研費 21H05054, 22H03639，23H03418 の支援と，東京大学の齋藤佑樹博士, 佐伯高明氏の協力を受け実施 したものです.}
}

音声合成

対照学習モデルによる音声-声質表現文の埋め込み表現獲得

渡邊亞椰 , 高道慎之介 , 齋藤佑樹 , and 3 more authors

In 日本音響学会春季研究発表会 , 2024

Bib PDF

@inproceedings{watanabe24asjs_coconut-embedding,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {対照学習モデルによる音声-声質表現文の埋め込み表現獲得},
  author = {亞椰, 渡邊 and 慎之介, 高道 and 佑樹, 齋藤 and 亘, 中田 and 徳泰, 辛 and 洋, 猿渡},
  year = {2024},
  memo = {本研究は科研費 21H04900, 22H03639，23H03418，JST 創発的研究支援事業 JP23KJ0828，ムーンショット JPMJPS2011 の助成を受けたものです.}
}

音声合成

F0に基づいて伸縮された画像文字からの音声合成

大中緋慧 , 宮崎亮一 , and 高道慎之介

In 日本音響学会春季研究発表会 , 2024

Bib PDF Slides

@inproceedings{ohnaka24asjs_vtts-width,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {{F0}に基づいて伸縮された画像文字からの音声合成},
  author = {緋慧, 大中 and 亮一, 宮崎 and 慎之介, 高道},
  year = {2024},
  memo = {本研究は，科研費 22H03639，21H04900 による補助を受けた}
}

コーパス

YODAS：YouTube 動画から構築される多言語大規模音声データセット

Xinjian Li , 高道慎之介 , 佐伯高明 , and 3 more authors

In 日本音響学会春季研究発表会 , 2024

Bib PDF Slides

@inproceedings{li24asjs_yodas,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {{YODAS：YouTube} 動画から構築される多言語大規模音声データセット},
  author = {Li, Xinjian and 慎之介, 高道 and 高明, 佐伯 and Chen, William and 塩田さやか and 晋治, 渡部},
  year = {2024},
  memo = {本研究は，アメリカ国立科学財団資金番号 #2138259, #2138286, #2138307, #2137603, #2138296 により支援さ れた，PSC Bridges2 と NCSA Delta via ACCESS allocation CIS210014 を使用した．また本研究は科研費 21H04900, 22H03639，23H03418，JST 創発的研究支援事業 JP23KJ0828， ムーンショット JPMJPS2011 の助成を受けた．}
}

音声合成

Diversity-based core-set selection for text-to-speech with linguistic and acoustic features

Kentaro Seki , Shinnosuke Takamichi , Takaaki Saeki , and 1 more author

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2024

arXiv Bib

@inproceedings{seki24icassp_core-set-selection,
  abbr_publisher = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Diversity-based core-set selection for text-to-speech with linguistic and acoustic features},
  author = {Seki, Kentaro and Takamichi, Shinnosuke and Saeki, Takaaki and Saruwatari, Hiroshi},
  year = {2024}
}

音声分析

Do learned speech symbols follow Zipf’s law?

Shinnosuke Takamichi , Hiroki Maeda , Joonyong Park , and 2 more authors

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2024

arXiv Bib

@inproceedings{meada24icassp_zipf-law,
  abbr_publisher = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Do learned speech symbols follow {Z}ipf's law?},
  author = {Takamichi, Shinnosuke and Maeda, Hiroki and Park, Joonyong and Saito, Daisuke and Saruwatari, Hiroshi},
  year = {2024}
}

音響合成

Environmental sound synthesis from vocal imitations and sound event labels

Yuki Okamoto , Keisuke Imoto , Shinnosuke Takamichi , and 3 more authors

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2024

arXiv Bib

@inproceedings{okamoto24icassp_enbironmental-synthesis,
  abbr_publisher = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Environmental sound synthesis from vocal imitations and sound event labels},
  author = {Okamoto, Yuki and Imoto, Keisuke and Takamichi, Shinnosuke and Nagase, Ryotaro and Fukumori, Takahiro and Yamashita, Yoichi},
  year = {2024}
}

NecoBERT：音声合成のために事前学習された自己教師あり学習モデル

中田亘 , 佐伯高明 , 齋藤佑樹 , and 2 more authors

In 日本音響学会春季研究発表会 , Mar 2024

PDF

2023

歌声合成

jaCappellaコーパスv2：重唱分離・合成のための日本語アカペラ重唱コーパスの拡張

中村友彦 , 高道慎之介 , 丹治尚子 , and 2 more authors

In 情報処理学会音楽情報科学研究会 , Mar 2023

Bib PDF

@inproceedings{nakamura23mus_jacappella-v2,
  abbr_publisher = {情報処理学会 音楽情報科学研究会},
  booktitle = {情報処理学会 音楽情報科学研究会},
  title = {{jaCappella}コーパスv2：重唱分離・合成のための日本語アカペラ重唱コーパスの拡張},
  author = {友彦, 中村 and 慎之介, 高道 and 尚子, 丹治 and 覚, 深山 and 洋, 猿渡},
  year = {2023},
}

コーパス

jaCappella corpus: A Japanese a cappella vocal ensemble corpus

Tomohiko Nakamura , Shinnosuke Takamichi , Naoko Tanji , and 2 more authors

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Mar 2023

arXiv Bib Website

@inproceedings{nakamura23icassp_jacappella,
  abbr_publisher = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {{jaCappella} corpus: A Japanese a cappella vocal ensemble corpus},
  author = {Nakamura, Tomohiko and Takamichi, Shinnosuke and Tanji, Naoko and Fukayama, Satoru and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

Mid-attribute Speaker Generation using Optimal-Transport-based Interpolation of Gaussian Mixture Models

Aya Watanabea , Shinnosuke Takamichi , Yuki Saito , and 2 more authors

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Mar 2023

arXiv Bib Code Website

@inproceedings{watanabe23icassp_mid-attribute,
  abbr_publisher = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Mid-attribute Speaker Generation using Optimal-Transport-based Interpolation of Gaussian Mixture Models},
  author = {Watanabea, Aya and Takamichi, Shinnosuke and Saito, Yuki and Xin, Detai and Saruwatari, Hiroshi},
  year = {2023}
}

音声分析

How Generative Spoken Language Model Encodes Noisy Speech: Investigation from Phonetics to Syntactics

Joonyong Park , Shinnosuke Takamichi , Tomohiko Nakamura , and 3 more authors

In Proceedings of Interspeech , Mar 2023

arXiv Bib

@inproceedings{park23interspeech_gslm,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {How Generative Spoken Language Model Encodes Noisy Speech: Investigation from Phonetics to Syntactics},
  author = {Park, Joonyong and Takamichi, Shinnosuke and Nakamura, Tomohiko and Seki, Kentaro and Xin, Detai and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

Improving robustness of spontaneous speech synthesis with linguistic speech regularization and pseudo-filled-pause insertion

Yuta Matsunaga , Takaaki Saeki , Shinnosuke Takamichi , and 1 more author

In Proceedings of Speech Synthesis Workshop (SSW) , Mar 2023

arXiv Bib Website

@inproceedings{matsunaga23ssw_filler-synthesis,
  abbr_publisher = {Proceedings of Speech Synthesis Workshop (SSW)},
  booktitle = {Proceedings of Speech Synthesis Workshop (SSW)},
  title = {Improving robustness of spontaneous speech synthesis with linguistic speech regularization and pseudo-filled-pause insertion},
  author = {Matsunaga, Yuta and Saeki, Takaaki and Takamichi, Shinnosuke and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining

Takaaki Saeki , Soumi Maiti , Xinjian Li , and 3 more authors

In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) , Mar 2023

arXiv Bib Code

@inproceedings{saeki23ijcai_learning-to-speak,
  abbr_publisher = {Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)},
  booktitle = {Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)},
  title = {Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining},
  author = {Saeki, Takaaki and Maiti, Soumi and Li, Xinjian and Watanabe, Shinji and Takamichi, Shinnosuke and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

Visual onoma-to-wave: environmental sound synthesis from visual onomatopoeias and sound-source images

Hien Ohnaka , Shinnosuke Takamichi , Keisuke Imoto , and 3 more authors

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Mar 2023

arXiv Bib Website

@inproceedings{ohnaka23icassp_visual-onoma-to-wave,
  abbr_publisher = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Visual onoma-to-wave: environmental sound synthesis from visual onomatopoeias and sound-source images},
  author = {Ohnaka, Hien and Takamichi, Shinnosuke and Imoto, Keisuke and Okamoto, Yuki and Fujii, Kazuki and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection

Kentaro Seki , Shinnosuke Takamichi , Takaaki Saeki , and 1 more author

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Mar 2023

arXiv Bib

@inproceedings{seki23icassp_dark-data,
  abbr_publisher = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection},
  author = {Seki, Kentaro and Takamichi, Shinnosuke and Saeki, Takaaki and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control

Aya Watanabe , Shinnosuke Takamichi , Yuki Saito , and 3 more authors

In IEEE Automatic Speech Recogiton and Understanding Workshop (ASRU) , Mar 2023

arXiv Bib Website

@inproceedings{watanabe23asru_coconut-corpus,
  abbr_publisher = {IEEE Automatic Speech Recogiton and Understanding Workshop (ASRU)},
  booktitle = {IEEE Automatic Speech Recogiton and Understanding Workshop (ASRU)},
  title = {{Coco-Nut}: Corpus of {J}apanese Utterance and Voice Characteristics Description for Prompt-based Control},
  author = {Watanabe, Aya and Takamichi, Shinnosuke and Saito, Yuki and Nakata, Wataru and Xin, Detai and Saruwatari, Hiroshi},
  year = {2023}
}

コーパス

YODAS: Youtube-Oriented Dataset for Audio and Speech

Xinjian Li , Shinnosuke Takamichi , Takaaki Saeki , and 3 more authors

In Proc. ASRU , Dec 2023

PDF
Speaking Practice Using Text-to-speech Technology: Japanese EFL Learners’ Perceptions

Yasushige Ishikawa , Shinnosuke Takamichi , Yuta Matsunaga , and 2 more authors

In WorldCALL , Nov 2023
コーパス

CALLS: Japanese empathetic dialogue speech corpus of complaint handling and attentive listening in customer center

Yuki Saito , Eiji Iimori , Shinnosuke Takamichi , and 2 more authors

In Proceedings of Interspeech , Aug 2023

PDF
音声合成

ChatGPT-EDSS: empathetic dialogue speech synthesis trained from ChatGPT-derived context word embeddings

Yuki Saito , Shinnosuke Takamichi , Eiji Iimori , and 2 more authors

In Proceedings of Interspeech , Aug 2023

PDF
音響合成

Foley Sound Synthesis at the DCASE 2023 Challenge

Keunwoo Choi , Jaekwon Im , Laurie Heller , and 5 more authors

In DCASE Challenge , May 2023

arXiv
Effects of text-to-speech synthesized speech on learners’ presentation anxiety and self-efficacy: A comparison of two models

Takatoyo Umemoto , Shinnosuke Takamichi , Yuta Matsunaga , and 5 more authors

In Proc. EUROCALL , Aug 2023
音声合成

Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with Acoustic and Textual Contexts

Detai Xin , Sharath Adavanne , Federico Ang , and 3 more authors

In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , Jun 2023

PDF
TimToShape: Supporting Practice of Musical Instruments by Visualizing Timbre with 2D Shapes based on Crossmodal Correspondences

Kota Arai , Yutaro Hirao , Takuji Narumi , and 3 more authors

In Proc. IUI , Mar 2023

PDF

音声合成

Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus

Detai Xin , Shinnosuke Takamichi , Ai Morimatsu , and 1 more author

In Proceedings of Interspeech , Mar 2023

arXiv Bib Website

@inproceedings{xin23interspeech_laughter-synthesis,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {Laughter Synthesis using Pseudo Phonetic Tokens with a Large-scale In-the-wild Laughter Corpus},
  author = {Xin, Detai and Takamichi, Shinnosuke and Morimatsu, Ai and Saruwatari, Hiroshi},
  memo = {This work was supported by JST SPRING, Grant Number JPMJSP2108, JSPS KAKENHI, Grant Number JP23KJ0828, and JST FOREST JPMJFR226V.},
  year = {2023}
}

音声合成

HumanDiffusion: diffusion model using perceptual gradients

Yota Ueda , Shinnosuke Takamichi , Yuki Saito , and 2 more authors

In Proceedings of Interspeech , Mar 2023

arXiv Bib

@inproceedings{ueda23interspeech_humandiffusion,
  abbr_publisher = {Proceedings of Interspeech},
  booktitle = {Proceedings of Interspeech},
  title = {HumanDiffusion: diffusion model using perceptual gradients},
  author = {Ueda, Yota and Takamichi, Shinnosuke and Saito, Yuki and Takamune, Norihiro and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

vTTS: visual-text to speech

Yoshifumi Nakano , Takaaki Saeki , Shinnosuke Takamichi , and 2 more authors

In Proceedings of IEEE Spoken Language Technology Workshop (SLT) , Mar 2023

arXiv Bib Code Slides

@inproceedings{nakano23slt_visual-text-to-speech,
  abbr_publisher = {Proceedings of IEEE Spoken Language Technology Workshop (SLT)},
  booktitle = {Proceedings of IEEE Spoken Language Technology Workshop (SLT)},
  title = {{vTTS}: visual-text to speech},
  author = {Nakano, Yoshifumi and Saeki, Takaaki and Takamichi, Shinnosuke and Sudoh, Katsuhito and Saruwatari, Hiroshi},
  year = {2023}
}

音声合成

Coco-Nut: 自由記述文による声質制御に向けた多話者音声・声質自由記述ペアデータセット

渡邊亞椰 , 高道慎之介 , 齋藤佑樹 , and 2 more authors

In 日本音響学会秋季研究発表会 , Mar 2023

Bib PDF Slides Website

@inproceedings{watanabe23asja_coconut,
  abbr_publisher = {日本音響学会秋季研究発表会},
  booktitle = {日本音響学会秋季研究発表会},
  title = {Coco-Nut: 自由記述文による声質制御に向けた多話者音声・声質自由記述ペアデータセット},
  author = {亞椰, 渡邊 and 慎之介, 高道 and 佑樹, 齋藤 and 徳泰, 辛 and 洋, 猿渡},
  year = {2023}
}

音声合成

深層学習で獲得される音声シンボルは自然言語シンボルと同様に Zipf 則に従うか？

前田紘希 , 高道慎之介 , 朴浚鎔 , and 1 more author

In 日本音響学会秋季研究発表会 , Mar 2023

Bib PDF Slides

@inproceedings{maeda23asja_zipf,
  abbr_publisher = {日本音響学会秋季研究発表会},
  booktitle = {日本音響学会秋季研究発表会},
  title = {深層学習で獲得される音声シンボルは自然言語シンボルと同様に {Zipf} 則に従うか？},
  author = {紘希, 前田 and 慎之介, 高道 and 浚鎔, 朴 and 洋, 猿渡},
  year = {2023}
}

音声合成

学習・評価ループを用いたデータ選択によるダークデータからの音声合成

関健太郎 , 高道慎之介 , 佐伯高明 , and 1 more author

In 日本音響学会春季研究発表会 , Mar 2023

Bib PDF

@inproceedings{seki23asjs_dark-data,
  abbr_publisher = {日本音響学会春季研究発表会},
  booktitle = {日本音響学会春季研究発表会},
  title = {学習・評価ループを用いたデータ選択によるダークデータからの音声合成},
  author = {健太郎, 関 and 慎之介, 高道 and 高明, 佐伯 and 洋, 猿渡},
  year = {2023}
}

音響合成

Voice-to-foley: 環境音を模倣した音声を入力とする環境音合成

岡本悠希 , 井本桂右 , 高道慎之介 , and 4 more authors

In 日本音響学会秋季研究発表会 , Mar 2023

Bib

@inproceedings{okamoto23asja_voice-to-fokey,
  abbr_publisher = {日本音響学会秋季研究発表会},
  booktitle = {日本音響学会秋季研究発表会},
  title = {Voice-to-foley: 環境音を模倣した音声を入力とする環境音合成},
  author = {悠希, 岡本 and 桂右, 井本 and 慎之介, 高道 and 亮太郎, 永瀬 and 隆寛, 福森 and 洋一 and 山下},
  year = {2023}
}

テキスト音声合成におけるデータサブセット選択のための指標検討

関健太郎 , 高道慎之介 , 佐伯高明 , and 1 more author

In 日本音響学会秋季研究発表会 , Sep 2023

PDF

AI音声合成の技術動向

高道慎之介

CEDEC 2023, Aug 2023

(Invited talk / 招待講演)

Bib Slides

@article{takamichi23cedec_copyright,
  title = {AI音声合成の技術動向},
  author = {慎之介, 高道},
  year = {2023},
  journal = {CEDEC 2023},
  month = aug,
  note = {(Invited talk / 招待講演)},
}

ここまで来た＆これから来る歌声合成・歌声変換技術

高道慎之介

音楽情報科学研究会夏のシンポジウム, Aug 2023

(Invited talk / 招待講演)

Bib Slides

@article{takamichi23asj_keio-talk,
  title = {ここまで来た＆これから来る歌声合成・歌声変換技術},
  author = {慎之介, 高道},
  year = {2023},
  journal = {音楽情報科学研究会 夏のシンポジウム},
  month = aug,
  note = {(Invited talk / 招待講演)},
}

音声の基盤モデルが切り拓く未来

高道慎之介

第24回慶應科学技術展, Dec 2023

(Invited talk / 招待講演)

Bib Slides

@article{takamichi23keio_talk,
  title = {音声の基盤モデルが切り拓く未来},
  author = {慎之介, 高道},
  year = {2023},
  journal = 第24回慶應科学技術展,
  month = dec,
  note = {(Invited talk / 招待講演)},
}

機械学習を用いた波形モデリング〜人間の音声の場合〜

高道慎之介

日本地球惑星科学連合2023年大会, May 2023

(Invited talk / 招待講演)

Bib Slides

@article{takamichi23asj_keio-tall,
  title = {機械学習を用いた波形モデリング 〜人間の音声の場合〜},
  author = {慎之介, 高道},
  year = {2023},
  journal = 日本地球惑星科学連合2023年大会,
  month = may,
  note = {(Invited talk / 招待講演)},
}