Segmental RNN

Closed weights University of Edinburgh,Carnegie Mellon University (CMU),University of Washington June 2016

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
University of Edinburgh,Carnegie Mellon University (CMU),University of Washington
Organisation type
Academia,Academia,Academia
Country
United Kingdom of Great Britain and Northern Ireland, United States of America
Published
20 June 2016
Authors
Liang Lu, Lingpeng Kong, Chris Dyer, Noah A. Smith, Steve Renals

What it does

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

Domain
Speech
Task
Speech recognition (ASR)
Approach
Supervised

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
tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased

How it is classified

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

Why it is tracked
SOTA improvement

https://paperswithcode.com/sota/speech-recognition-on-timit

Record confidence
Unknown

Sources

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

Reference
Segmental Recurrent Neural Networks for End-to-end Speech Recognition
Last updated
28 November 2025

What the numbers mean

Where it came from

Segmental RNN was published by University of Edinburgh,Carnegie Mellon University (CMU),University of Washington, in United Kingdom of Great Britain and Northern Ireland, in June 2016. It comes out of academia,Academia,Academia.

It works in Speech, and is recorded as doing speech recognition (ASR).

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

Segmental RNN — common questions

01

Who created Segmental RNN?

Segmental RNN was published by University of Edinburgh,Carnegie Mellon University (CMU),University of Washington, based in United Kingdom of Great Britain and Northern Ireland, categorised as academia,Academia,Academia.

02

When was Segmental RNN released?

Segmental RNN was published in June 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is Segmental RNN used for?

Segmental RNN works in Speech, and is recorded as handling 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.

04

What GPU do I need to run Segmental RNN?

None. Segmental RNN 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.

05

Is Segmental RNN open source?

No. Segmental RNN has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does Segmental RNN have?

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

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.