Six Presentations at ICASSP 2026

2026

1. SPATIAL-CLAP: LEARNING SPATIALLY-AWARE AUDIO–TEXT EMBEDDINGS FOR MULTI-SOURCE CONDITIONS

   Kentaro Seki ,  Yuki Okamoto ,  Kouei Yamaoka ,  Yuki Saito ,  Shinnosuke Takamichi ,  and  Hiroshi Saruwatari

   In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2026

   Bib

   @inproceedings{seki26icassp_spatial-clap,
     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 = {SPATIAL-CLAP: LEARNING SPATIALLY-AWARE AUDIO–TEXT EMBEDDINGS FOR MULTI-SOURCE CONDITIONS},
     author = {Seki, Kentaro and Okamoto, Yuki and Yamaoka, Kouei and Saito, Yuki and Takamichi, Shinnosuke and Saruwatari, Hiroshi},
     year = {2026},
     month = may
   }

2. TTSOPS: A CLOSED-LOOP CORPUS OPTIMIZATION FRAMEWORK FOR TRAINING MULTI-SPEAKER TTS MODELS FROM DARK DATA

   Kentaro Seki ,  Shinnosuke Takamichi ,  Takaaki Saeki ,  and  Hiroshi Saruwatari

   In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2026

   Bib

   @inproceedings{seki26icassp_ttsops,
     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 = {TTSOPS: A CLOSED-LOOP CORPUS OPTIMIZATION FRAMEWORK FOR TRAINING MULTI-SPEAKER TTS MODELS FROM DARK DATA},
     author = {Seki, Kentaro and Takamichi, Shinnosuke and Saeki, Takaaki and Saruwatari, Hiroshi},
     year = {2026},
     month = may
   }

3. XACLE Challenge 2026: The first x-to-audio alignment challenge

   Yuki Okamoto ,  Riki Takizawa ,  Minoru Kishi ,  Yusuke Kanamori ,  Noriyuki Tonami ,  Ryotaro Nagase ,  Shinnosuke Takamichi ,  and  Keisuke Imoto

   In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2026

   Bib

   @inproceedings{okamoto26icassp_xacle-challenge,
     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 = {XACLE Challenge 2026: The first x-to-audio alignment challenge},
     author = {Okamoto, Yuki and Takizawa, Riki and Kishi, Minoru and Kanamori, Yusuke and Tonami, Noriyuki and Nagase, Ryotaro and Takamichi, Shinnosuke and Imoto, Keisuke},
     year = {2026},
     month = may
   }

4. MANGAVOX: DATASET OF ACTED VOICES ALIGNED WITH MANGA IMAGES TOWARDS COMPUTER UNDERSTANDING OF AUDIO COMICS

   Shinnosuke Takamichi ,  Tomohiko Nakamura ,  Hitoshi Suda ,  Satoru Fukayama ,  and  Jun Ogata

   In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2026

   Bib

   @inproceedings{takamichi26icassp_mangavox,
     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 = {MANGAVOX: DATASET OF ACTED VOICES ALIGNED WITH MANGA IMAGES TOWARDS COMPUTER UNDERSTANDING OF AUDIO COMICS},
     author = {Takamichi, Shinnosuke and Nakamura, Tomohiko and Suda, Hitoshi and Fukayama, Satoru and Ogata, Jun},
     year = {2026},
     month = may
   }

5. SS-JDSC: SINGLE-SPEAKER JAPANESE DYSARTHRIC SPEECH CORPUS

   Asahi Ogasawara ,  Shinnosuke Takamichi ,  Jianing Yang ,  Go Suenaga ,  and  Yiyu Tan

   In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2026

   Bib

   @inproceedings{ogasawara26icassp_ss-jdsc,
     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 = {SS-JDSC: SINGLE-SPEAKER JAPANESE DYSARTHRIC SPEECH CORPUS},
     author = {Ogasawara, Asahi and Takamichi, Shinnosuke and Yang, Jianing and Suenaga, Go and Tan, Yiyu},
     year = {2026},
     month = may
   }

6. THREE-STAGE BSRNN FOR UNIVERSAL SPEECH ENHANCEMENT AND DATA CURATION USING A LARGE PRE-TRAINED SPEECH RESTORATION MODEL

   Ryutaro Matsunaga ,  Ryo Takahashi ,  and  Shinnosuke Takamichi

   In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2026

   Bib

   @inproceedings{matsunaga26icassp_three-stage-bsrnn,
     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 = {THREE-STAGE BSRNN FOR UNIVERSAL SPEECH ENHANCEMENT AND DATA CURATION USING A LARGE PRE-TRAINED SPEECH RESTORATION MODEL},
     author = {Matsunaga, Ryutaro and Takahashi, Ryo and Takamichi, Shinnosuke},
     year = {2026},
     month = may
   }