Takaaki Saeki

52 papers A* 1A 6B 2C 2Misc 7Journal 30Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Speaker-conditioned phrase break prediction for text-to-speech with phoneme-level pre-trained language model.
Speech Commun.
Dong Yang, Yuki Saito, Takaaki Saeki, Tomoki Koriyama, Wataru Nakata, Detai Xin, Hiroshi Saruwatari
2025 — conf
Active Learning for Text-to-Speech Synthesis with Informative Sample Collection.
APSIPA
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki, Hiroshi Saruwatari
2025 J jnl
Active Learning for Text-to-Speech Synthesis with Informative Sample Collection.
CoRR
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki, Hiroshi Saruwatari
2025 Misc conf
Speech Re-Painting for Robust ASR.
ICASSP
Kyle Kastner, Gary Wang, Isaac Elias, Takaaki Saeki, Pedro Moreno Mengibar, Françoise Beaufays, Andrew Rosenberg, Bhuvana Ramabhadran
2025 J jnl
TTSOps: A Closed-Loop Corpus Optimization Framework for Training Multi-Speaker TTS Models from Dark Data.
CoRR
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki, Hiroshi Saruwatari
2025 J jnl
Toward Data-Efficient Speech Synthesis: Active Learning-Based Corpus Construction for Multi-Speaker Text-to-Speech Synthesis.
IEEE Access
Kentaro Seki, Yuki Saito, Shinnosuke Takamichi, Takaaki Saeki, Hiroshi Saruwatari
2024 Misc conf
Diversity-Based Core-Set Selection for Text-to-Speech with Linguistic and Acoustic Features.
ICASSP
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki, Hiroshi Saruwatari
2024 Misc conf
Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data.
ICASSP
Takaaki Saeki, Gary Wang, Nobuyuki Morioka, Isaac Elias, Kyle Kastner, Andrew Rosenberg, Bhuvana Ramabhadran, Heiga Zen, Françoise Beaufays, Hadar Shemtov
2024 J jnl
Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data.
CoRR
Takaaki Saeki, Gary Wang, Nobuyuki Morioka, Isaac Elias, Kyle Kastner, Andrew Rosenberg, Bhuvana Ramabhadran, Heiga Zen, Françoise Beaufays, Hadar Shemtov
2024 — conf
NecoBERT: Self-Supervised Learning Model Trained by Masked Language Modeling on Rich Acoustic Features Derived from Neural Audio Codec.
APSIPA
Wataru Nakata, Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari
2024 A conf
SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics.
INTERSPEECH
Takaaki Saeki, Soumi Maiti, Shinnosuke Takamichi, Shinji Watanabe, Hiroshi Saruwatari
2024 J jnl
SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics.
CoRR
Takaaki Saeki, Soumi Maiti, Shinnosuke Takamichi, Shinji Watanabe, Hiroshi Saruwatari
2024 J jnl
Text-Inductive Graphone-Based Language Adaptation for Low-Resource Speech Synthesis.
IEEE ACM Trans. Audio Speech Lang. Process.
Takaaki Saeki, Soumi Maiti, Xinjian Li, Shinji Watanabe, Shinnosuke Takamichi, Hiroshi Saruwatari
2024 J jnl
YODAS: Youtube-Oriented Dataset for Audio and Speech.
CoRR
Xinjian Li, Shinnosuke Takamichi, Takaaki Saeki, William Chen, Sayaka Shiota, Shinji Watanabe
2023 J jnl
Diversity-based core-set selection for text-to-speech with linguistic and acoustic features.
CoRR
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki, Hiroshi Saruwatari
2023 Misc conf
Duration-Aware Pause Insertion Using Pre-Trained Language Model for Multi-Speaker Text-To-Speech.
ICASSP
Dong Yang, Tomoki Koriyama, Yuki Saito, Takaaki Saeki, Detai Xin, Hiroshi Saruwatari
2023 J jnl
Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-speech.
CoRR
Dong Yang, Tomoki Koriyama, Yuki Saito, Takaaki Saeki, Detai Xin, Hiroshi Saruwatari
2023 — conf
Improving robustness of spontaneous speech synthesis with linguistic speech regularization and pseudo-filled-pause insertion.
SSW
Yuta Matsunaga, Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2023 A* conf
Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining.
IJCAI
Takaaki Saeki, Soumi Maiti, Xinjian Li, Shinji Watanabe, Shinnosuke Takamichi, Hiroshi Saruwatari
2023 J jnl
Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining.
CoRR
Takaaki Saeki, Soumi Maiti, Xinjian Li, Shinji Watanabe, Shinnosuke Takamichi, Hiroshi Saruwatari
2023 J jnl
SelfRemaster: Self-Supervised Speech Restoration for Historical Audio Resources.
IEEE Access
Takaaki Saeki, Shinnosuke Takamichi, Tomohiko Nakamura, Naoko Tanji, Hiroshi Saruwatari
2023 Misc conf
Speechlmscore: Evaluating Speech Generation Using Speech Language Model.
ICASSP
Soumi Maiti, Yifan Peng, Takaaki Saeki, Shinji Watanabe
2023 Misc conf
Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-Speech.
ICASSP
Takaaki Saeki, Heiga Zen, Zhehuai Chen, Nobuyuki Morioka, Gary Wang, Yu Zhang, Ankur Bapna, Andrew Rosenberg, Bhuvana Ramabhadran
2023 C conf
Yodas: Youtube-Oriented Dataset for Audio and Speech.
ASRU
Xinjian Li, Shinnosuke Takamichi, Takaaki Saeki, William Chen, Sayaka Shiota, Shinji Watanabe
2022 A conf
DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning.
INTERSPEECH
Takaaki Saeki, Kentaro Tachibana, Ryuichi Yamamoto
2022 J jnl
DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning.
CoRR
Takaaki Saeki, Kentaro Tachibana, Ryuichi Yamamoto
2022 J jnl
Empirical Study Incorporating Linguistic Knowledge on Filled Pauses for Personalized Spontaneous Speech Synthesis.
CoRR
Yuta Matsunaga, Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2022 B conf
Personalized Filled-pause Generation with Group-wise Prediction Models.
LREC
Yuta Matsunaga, Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2022 J jnl
Personalized filled-pause generation with group-wise prediction models.
CoRR
Yuta Matsunaga, Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2022 B conf
SSR7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech Recognition.
LREC
Naoki Kimura, Zixiong Su, Takaaki Saeki, Jun Rekimoto
2022 A conf
SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling.
INTERSPEECH
Takaaki Saeki, Shinnosuke Takamichi, Tomohiko Nakamura, Naoko Tanji, Hiroshi Saruwatari
2022 J jnl
SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling.
CoRR
Takaaki Saeki, Shinnosuke Takamichi, Tomohiko Nakamura, Naoko Tanji, Hiroshi Saruwatari
2022 J jnl
SpeechLMScore: Evaluating speech generation using speech language model.
CoRR
Soumi Maiti, Yifan Peng, Takaaki Saeki, Shinji Watanabe
2022 J jnl
Spontaneous speech synthesis with linguistic-speech consistency training using pseudo-filled pauses.
CoRR
Yuta Matsunaga, Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2022 J jnl
Text-to-speech synthesis from dark data with evaluation-in-the-loop data selection.
CoRR
Kentaro Seki, Shinnosuke Takamichi, Takaaki Saeki, Hiroshi Saruwatari
2022 A conf
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022.
INTERSPEECH
Takaaki Saeki, Detai Xin, Wataru Nakata, Tomoki Koriyama, Shinnosuke Takamichi, Hiroshi Saruwatari
2022 J jnl
UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022.
CoRR
Takaaki Saeki, Detai Xin, Wataru Nakata, Tomoki Koriyama, Shinnosuke Takamichi, Hiroshi Saruwatari
2022 — conf
VTTS: Visual-Text To Speech.
SLT
Yoshifumi Nakano, Takaaki Saeki, Shinnosuke Takamichi, Katsuhito Sudoh, Hiroshi Saruwatari
2022 J jnl
Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech.
CoRR
Takaaki Saeki, Heiga Zen, Zhehuai Chen, Nobuyuki Morioka, Gary Wang, Yu Zhang, Ankur Bapna, Andrew Rosenberg, Bhuvana Ramabhadran
2022 J jnl
vTTS: visual-text to speech.
CoRR
Yoshifumi Nakano, Takaaki Saeki, Shinnosuke Takamichi, Katsuhito Sudoh, Hiroshi Saruwatari
2021 J jnl
ESPnet2-TTS: Extending the Edge of TTS Research.
CoRR
Tomoki Hayashi, Ryuichi Yamamoto, Takenori Yoshimura, Peter Wu, Jiatong Shi, Takaaki Saeki, Yooncheol Ju, Yusuke Yasuda, Shinnosuke Takamichi, Shinji Watanabe
2021 J jnl
Incremental Text-to-Speech Synthesis Using Pseudo Lookahead With Large Pretrained Language Model.
IEEE Signal Process. Lett.
Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2021 J jnl
JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verification.
CoRR
Shinnosuke Takamichi, Ludwig Kürzinger, Takaaki Saeki, Sayaka Shiota, Shinji Watanabe
2021 C conf
Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network.
ASRU
Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2021 J jnl
Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network.
CoRR
Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2021 J jnl
Real-Time Full-Band Voice Conversion with Sub-Band Modeling and Data-Driven Phase Estimation of Spectral Differentials.
IEICE Trans. Inf. Syst.
Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari
2020 A conf
End-to-End Deep Learning Speech Recognition Model for Silent Speech Challenge.
INTERSPEECH
Naoki Kimura, Zixiong Su, Takaaki Saeki
2020 J jnl
Incremental Text-to-Speech Synthesis Using Pseudo Lookahead with Large Pretrained Language Model.
CoRR
Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari
2020 Misc conf
Lifter Training and Sub-Band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials.
ICASSP
Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari
2020 J jnl
Lifter Training and Sub-band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials.
CoRR
Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari
2020 A conf
Real-Time, Full-Band, Online DNN-Based Voice Conversion System Using a Single CPU.
INTERSPEECH
Takaaki Saeki, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari
2010 J jnl
Impact and Use of the Asymmetric Property in Bi-directional Cooperative Relaying under Asymmetric Traffic Conditions.
IEICE Trans. Commun.
Takaaki Saeki, Koji Yamamoto, Hidekazu Murata, Susumu Yoshida