Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition — mentioned by albertzeyer

Thu, 09 Oct 2014 07:38:56 GMT

For example, the Switchboard corpus (300h, 8khz, transcribed audio) is about 16GB. That is a common size for LVCSR, and you need something around that area to get good performance (maybe minimum 100h). In academic papers by Google, they usually use their own private training data set, with e.g. 1900h. (E.g.: http://arxiv.org/pdf/1402.1128.pdf) Some crowdsourced effort to collect transcribed audio under a CC-licence would be great!

Paper and discussion history. A mention is not an endorsement.

Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition · HackerPapers discussions

Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition — mentioned by albertzeyer