Speaker-independent vowel classification

Training compute

7.5×10⁹ FLOP

Parameters

3K

Published

Nov 27, 1989

Speaker-independent vowel classification is an AI model developed by University of Washington (United States), first published in November 1989. It works in the speech domain, on tasks such as speech recognition (asr).

Training it took an estimated 7.5×10⁹ FLOP of compute (estimation method: operation counting). The model has 3,040 parameters. It was trained on roughly 4.1K datapoints.

Epoch AI rates the confidence of this record as confident.

Full record

Organization: University of Washington
Country of organization: United States
Domain: Speech
Task: Speech recognition (ASR)
Training compute: 7.5×10⁹ FLOP
Compute estimation method: Operation counting
Parameters: 3,040
Dataset size: 4.1K
Epoch confidence: Confident