Heiga Zen
E200563
Heiga Zen is a researcher in speech synthesis and machine learning, known for helping develop Google's WaveNet neural network for generating raw audio.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Heiga Zen canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T1793226 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heiga Zen Context triple: [WaveNet, introducedBy, Heiga Zen]
-
A.
Kobo Daishi
Kobo Daishi, also known as Kukai, was a Japanese Buddhist monk, scholar, and founder of the Shingon school of esoteric Buddhism who became one of Japan’s most revered religious figures.
-
B.
Dogenzaka
Dogenzaka is a lively entertainment and shopping district in Shibuya, Tokyo, known for its nightlife, restaurants, and proximity to the famous Shibuya Crossing.
-
C.
Zen Master
Zen Master is the famous nickname of legendary NBA coach Phil Jackson, known for his calm, philosophical approach and record-setting championship success with the Chicago Bulls and Los Angeles Lakers.
-
D.
Saigyō
Saigyō was a renowned late Heian and early Kamakura period Japanese Buddhist monk and poet celebrated for his deeply reflective waka poetry on nature, impermanence, and spiritual longing.
-
E.
Nakae Chōmin
Nakae Chōmin was a prominent Meiji-era Japanese political thinker, journalist, and translator who helped introduce Western liberal ideas to Japan and became a leading advocate for democracy and civil rights.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Heiga Zen Target entity description: Heiga Zen is a researcher in speech synthesis and machine learning, known for helping develop Google's WaveNet neural network for generating raw audio.
-
A.
Kobo Daishi
Kobo Daishi, also known as Kukai, was a Japanese Buddhist monk, scholar, and founder of the Shingon school of esoteric Buddhism who became one of Japan’s most revered religious figures.
-
B.
Dogenzaka
Dogenzaka is a lively entertainment and shopping district in Shibuya, Tokyo, known for its nightlife, restaurants, and proximity to the famous Shibuya Crossing.
-
C.
Zen Master
Zen Master is the famous nickname of legendary NBA coach Phil Jackson, known for his calm, philosophical approach and record-setting championship success with the Chicago Bulls and Los Angeles Lakers.
-
D.
Saigyō
Saigyō was a renowned late Heian and early Kamakura period Japanese Buddhist monk and poet celebrated for his deeply reflective waka poetry on nature, impermanence, and spiritual longing.
-
E.
Nakae Chōmin
Nakae Chōmin was a prominent Meiji-era Japanese political thinker, journalist, and translator who helped introduce Western liberal ideas to Japan and became a leading advocate for democracy and civil rights.
- F. None of above. chosen
Statements (33)
| Predicate | Object |
|---|---|
| instanceOf |
person
ⓘ
researcher ⓘ |
| affiliation | IEEE ⓘ |
| educatedAt | Nagoya Institute of Technology ⓘ |
| employer |
Google
ⓘ
Google DeepMind ⓘ
linked to:
DeepMind
|
| fieldOfStudy |
information engineering
ⓘ
speech processing ⓘ |
| fieldOfWork |
machine learning
ⓘ
speech synthesis ⓘ statistical parametric speech synthesis ⓘ |
| hasAcademicDegree | PhD ⓘ |
| hasCitizenship | Japan ⓘ |
| hasPublicationType |
conference papers
ⓘ
journal articles ⓘ |
| hasPublicationVenue |
ICASSP
ⓘ
ICML ⓘ INTERSPEECH ⓘ NeurIPS ⓘ |
| hasRole |
author
ⓘ
research scientist ⓘ team lead ⓘ |
| knownFor |
contributions to WaveNet
ⓘ
neural network-based speech synthesis ⓘ |
| language |
English
ⓘ
Japanese ⓘ |
| notableWork |
WaveNet: A Generative Model for Raw Audio
ⓘ
linked to:
WaveNet
statistical parametric speech synthesis using HMMs ⓘ |
| researchInterest |
deep generative models for audio
ⓘ
end-to-end text-to-speech ⓘ neural vocoders ⓘ sequence modeling ⓘ |
| workLocation |
London
ⓘ
linked to:
London, England
|
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Heiga Zen Description of subject: Heiga Zen is a researcher in speech synthesis and machine learning, known for helping develop Google's WaveNet neural network for generating raw audio.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.