Time-delay neural networks

Closed weights Advanced Telecommunications Research Institute,Carnegie Mellon University (CMU) March 1989

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Advanced Telecommunications Research Institute,Carnegie Mellon University (CMU)
Organisation type
Industry,Academia
Country
Japan, United States of America
Published
3 March 1989
Authors
A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K. J. Lang

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Speech
Task
Speech recognition (ASR)

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
2,046 tokens

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Unknown
Citations
3,445

Sources

Where this record came from and when it was last checked.

Reference
Phoneme recognition using time-delay neural networks
Last updated
28 November 2025

What the numbers mean

Where it came from

Time-delay neural networks was published by Advanced Telecommunications Research Institute,Carnegie Mellon University (CMU), in the country recorded as Japan, during March 1989. The publishing organisation is categorised as industry,Academia.

It works in the domain of Speech, and is recorded as performing the task of speech recognition (ASR).

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

The training set ran to roughly 2,046 tokens of text.

Answers

Time-delay neural networks — common questions

01

Time-delay neural networks— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

02

Time-delay neural networks— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

Time-delay neural networks— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

04

Time-delay neural networks— who created it?

It was published by Advanced Telecommunications Research Institute,Carnegie Mellon University (CMU), based in Japan, an organisation categorised as industry,Academia.

05

Time-delay neural networks— when was it released?

It was published in March 1989. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

Time-delay neural networks— what is it used for?

It works in the domain of Speech, and is recorded as handling the task of speech recognition (ASR). A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.