5 papers accepted for Interspeech 2025

The following papers have been accepted for Interspeech 2025. Congrats to all!

  • Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models (東大 宮尾研)
  • Voice Conversion for Likability Control via Automated Rating of Speech Synthesis Corpora (産総研)
  • Japanese speaker verification and spoofing attacks recorded in-the-wild dataset (都立大)
  • RELATE: Subjective evaluation dataset for automatic evaluation of relevance between text and audio (東大 猿渡研)
  • The text-to-speech in the wild (TITW) dataset (CMU)

References

2025

  1. Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models
    Shunsuke Kando ,  Yusuke Miyao ,  and  Shinnosuke Takamichi
    In Proceedings of Interspeech , Aug 2025
  2. Voice Conversion for Likability Control via Automated Rating of Speech Synthesis Corpora
    Hitoshi Suda ,  Shinnosuke Takamichi ,  and  Satoru Fukayama
    In Proceedings of Interspeech , Aug 2025
  3. Japanese speaker verification and spoofing attacks recorded in-the-wild dataset
    Sayaka Shiota ,  Suzuka Horie ,  Kouta Kanno ,  and  Shinnosuke Takamichi
    In Proceedings of Interspeech , Aug 2025
  4. RELATE: Subjective evaluation dataset for automatic evaluation of relevance between text and audio
    Yusuke Kanamori ,  Yuki Okamoto ,  Taisei Takano ,  Shinnosuke TakamichiYuki Saito ,  and  Hiroshi Saruwatari
    In Proceedings of Interspeech , Aug 2025
  5. The text-to-speech in the wild (TITW) dataset
    Jee-weon Jung ,  Wangyou Zhang ,  Soumi Maiti ,  Yihan Wu ,  Xin Wang ,  Ji-Hoon Kim ,  Yuta Matsunaga ,  Seyun Um ,  Jinchuan Tian ,  Hye-jin Shim , and 4 more authors
    In Proceedings of Interspeech , Aug 2025