· 2013
Speech recognition with deep recurrent neural networks
- 8,855citations
- 2013year
Short summary
Deep Long Short-term Memory (LSTM) recurrent neural networks (RNNs) trained end-to-end achieved a 17.7% test set error on the TIMIT phoneme recognition benchmark, outperforming previous methods.
AI-generated from the title and abstract; the full text is not read.
TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app
The rest is in the Pofolia app
Takeaways, key points and questions to the paper; new summaries every day for your field. Free.
Sign in on the web to openField: Artificial Intelligence
Artificial IntelligenceComputer Science