LAB LOGA page on LabLog, a review site (not the lab's official page)
Speech Science Lab
Machine-translated · View original
A speech science lab exploring how humans produce voice and how it is heard and understood.
AboutAbout the lab
Measuring how the human voice is produced to understand it
The speech science lab of Assistant Professor Kohei Wakamiya aims to understand how humans produce voices with such a wide variety of voice qualities.
The lab wants to build a speech production model that imitates the mechanism of human speech, and is currently studying methods for measuring the movements of the articulators inside the mouth.
It also works on the intelligibility of interrupted or degraded speech, perceptual evaluation of hoarseness (a husky, rough voice), and detection of infectious diseases from the sound of coughs.
Key terms
- 3D electromagnetic articulography system
- A device that uses receiver coils as position markers and measures their positions in an alternating magnetic field. It is used to observe the movements of the articulators.
- Mosaic speech
- Speech made hard to understand by dividing it into blocks in frequency and time and processing noise using the average intensity of each block.
- Hoarseness
- A voice with disturbed quality, such as a husky or rough voice.
- GRBAS scale
- A framework for rating the quality of a pathological voice in stages based on listening impressions. Variability among raters is considered a challenge.
NewsLab news
View More ↗ResearchResearch themes
To understand how humans produce voices with such a wide variety of voice qualities, the lab wants to build a speech production model that imitates the mechanism of human speech. To that end, it studies methods for observing the articulators, and also researches the intelligibility of degraded speech, evaluation of hoarseness, and analysis of cough sounds.
*Illustrative imageDetecting Infectious Disease from Cough Sounds
This research determines from the sound of a cough whether a person has an infectious disease. The aim is to distinguish between a healthy state and an infected state.
*Illustrative imageIntelligibility of Interrupted Speech
The lab investigates how intelligibility changes when the gaps in mosaic speech are filled by stretching the speech segments. When the gaps are long, intelligibility can actually become worse. The lab has published a paper on this as joint research.
Automatic Estimation of Perceptual Evaluation of Hoarseness
This research uses deep learning to automatically estimate the GRBAS scale, which rates the quality of a hoarse voice based on listening impressions. A paper from joint research reports that, even with a small amount of rating data, automatic scoring was achieved at a level comparable to the variability among experts' ratings.
*Illustrative imageMeasuring and Analyzing Articulator Movements
This research measures the movements of the articulators inside the mouth with a 3D electromagnetic articulography system. The lab studies methods for collecting the basic data needed to build a speech production model that imitates the mechanism of human speech.
MembersFaculty
- Assistant ProfessorKohei Wakamiya
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 Speech Science Lab
Speech Science LabSchool of Design, Department of DesignSpeech science
Speech Information Processing LabSchool of Design, Department of DesignSpeech information processing
Speech Information Processing Lab (Tokihiko Kaburagi)School of Design, Department of DesignSpeech information processing
Color and Vision Science LabSchool of Design, Department of DesignColor and vision scienceThe 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: “Speech Production Organs - Numbered” Theresa Knott / CC BY-SA 2.5 (cropped)
- Detecting Infectious Disease from Cough Sounds: “Woman coughing” MelConfidentiel / CC BY 4.0 (cropped)
- Intelligibility of Interrupted Speech: “HearingExam” Flávia Costa / CC BY 3.0 (cropped)
- Measuring and Analyzing Articulator Movements: “Ultrasound Scan ND” Nevit Dilmen (talk) / CC BY-SA 3.0 (cropped)
- Related lab (Speech Science Lab): “Human Larynx Model ( )” YVC Biology Department / CC BY 2.0 (cropped)
- Related lab (Speech Information Processing Lab): “Tracto vocal” Itsnaaav / CC BY-SA 4.0 (cropped)
- Related lab (Speech Information Processing Lab (Tokihiko Kaburagi)): “Petra, People in conversation, Jordan” Vyacheslav Argenberg / CC BY 4.0 (cropped)
- Related lab (Color and Vision Science Lab): “Color-palette-dynamic-color” Vijay Verma / 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.