LAB LOGA page on LabLog, a review site (not the lab's official page)
Human Interface [(Omachi)-Nose] Lab
Machine-translated · View original
The lab works on speech processing and dialogue, using computers to handle sound, voice, and language.
AboutAbout the lab
Researching next-generation HCI centered on sound, voice, and language.
The (Omachi)-Nose Lab conducts research for next-generation HCI (human-computer interaction) centered on sound, voice, and language.
Its research themes include speech and singing voice synthesis and conversion, dialogue systems, speech emotion recognition, and restoration of degraded audio from old records.
The lab is developing systems that support online learning, and is also considering building an Audio Captioning model that describes environmental sounds in text.
The lab belongs to the Department of Communications Engineering, Graduate School of Engineering, Tohoku University.
Key terms
- HCI
- Short for Human Computer Interaction; the interaction between people and computers.
- Voice conversion
- A technology that changes only the speaker characteristics, that is, the vocal identity, while keeping the content of the speech.
- Self-supervised learning
- A machine learning method that learns features from the data itself, without humans providing correct labels.
- Audio Captioning
- A task that outputs, as a text caption, the scene inferred from an input environmental sound.
ResearchResearch themes
Toward next-generation HCI centered on sound, voice, and language, the lab works on speech and singing voice synthesis and conversion, dialogue systems, and speech emotion recognition. Many of its studies use deep learning or large language models.
*Illustrative imageSynthesizing Voices That Match Anime Characters' Faces
The lab aims to build text-to-speech synthesis that infers the speaker characteristics of a new character from a face image and synthesizes a voice that suits that character. Automatically assigning a voice to a character who does not exist in reality is difficult, and this is the central challenge.
*Illustrative imageSinging Voice Synthesis Using Musical Scores
In end-to-end singing voice synthesis that generates a singing voice from a musical score, the lab aims to build a model that uses the pitch and timing information in the score to improve the accuracy of pitch and rhythm estimation.
*Illustrative imageImproving Speech Models for Voice Conversion
In voice conversion, which changes only the speaker's vocal identity, the lab aims to achieve higher-quality conversion by adapting self-supervised speech models for voice conversion.
*Illustrative imageDialogue Systems That Draw on Past Conversations
Toward dialogue systems with long-term memory, the lab aims to optimize the retrieval of past dialogue records. It compares methods such as keyword search and vector search to find the one that suits the nature of the memory.
MembersFaculty
The members of the (Omachi)-Nose Lab consist of faculty, technical assistants, and doctoral, master's, and undergraduate students.As of 2026
- Associate ProfessorTakashi Nose
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Human Interface [(Omachi)-Nose] Lab
Information Kansei Engineering LabFaculty of Engineering, Department of Electrical, Information and Physics EngineeringDisplays that reproduce the material appearance of digital i…![Image of research at Image Information and Communication Engineering [Omachi-Miyazaki] Lab](/img/2f392f0a17bbf333-800.webp)
Image Information and Communication Engineering [Omachi-Miyazaki] LabFaculty of Engineering, Department of Electrical, Information and Physics EngineeringPattern recognition, image processing and image recognition,…
Novel-Concept VLSI Systems LabFaculty of Engineering, Department of Electrical, Information and Physics EngineeringNew computing with brain-inspired LSI; artificial intelligen…![Image of research at Green Power Electronics [Endoh (T.)] Lab](/img/54b2ddd9be870f64-800.webp)
Green Power Electronics [Endoh (T.)] LabFaculty of Engineering, Department of Electrical, Information and Physics EngineeringSemiconductor integrated circuits, power electronics, AI pro…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Neumann U87 Condenser Microphone - Studio A, In Your Ear Studios” Will Fisher from Richmond, VA, United States / CC BY-SA 2.0 (cropped)
- Synthesizing Voices That Match Anime Characters' Faces: “Gray cyan hair anime girl” Ao hoshi 03 / CC BY-SA 4.0 (cropped)
- Singing Voice Synthesis Using Musical Scores: “Chorus member singing (Unsplash)” David Beale davidbeale / CC0 (cropped)
- Improving Speech Models for Voice Conversion: “Audio mixer close up” Lchader / CC BY-SA 4.0 (cropped)
- Dialogue Systems That Draw on Past Conversations: “Harman Kardon Invoke Speaker - aerial” Jdubman / CC BY-SA 4.0 (cropped)
- Related lab (Information Kansei Engineering Lab): “IPS LCD panel” Jack Whittaker (https://jackw01.github.io) / CC0 (cropped)
- Related lab (Image Information and Communication Engineering [Omachi-Miyazaki] Lab): “Image processing post otsus algorithm” Pikez33 / CC BY 1.0 (cropped)
- Related lab (Novel-Concept VLSI Systems Lab): “A wafer consisting of MPC designs all over the wafer and five process control monitor (PCM) designs for ensuring good quality of the processing” Khpsoi / CC BY-SA 4.0 (cropped)
- Related lab (Green Power Electronics [Endoh (T.)] Lab): “Wafer scale integrated circuit on 300 mm wafer” Wikideas1 / CC0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.