AI models
RNN for speech
Training compute
2.3×10¹¹ FLOP
Parameters
7.5K
Published
May 15, 1998
RNN for speech is an AI model developed by National Chiao Tung University (Taiwan), first published in May 1998. It works in the speech domain, on tasks such as speech synthesis.
Training it took an estimated 2.3×10¹¹ FLOP of compute (estimation method: third-party estimation). The model has 7,512 parameters.
The reference paper has 231 citations.
Full record
- Organization
- National Chiao Tung University
- Country of organization
- Taiwan
- Domain
- Speech
- Task
- Speech synthesis
- Training compute
- 2.3×10¹¹ FLOP
- Compute estimation method
- Third-party estimation
- Parameters
- 7,512
- Citations
- 231
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models