Re:Oxford Deep NLP – An advanced course on natural language ...
by bshillingford on Tuesday February 07, 2017 @11:41AM
(#13590528)
Standard neural network-based speech recognition pipelines (i.e. RNN + CTC) always use a language model. Unlike a seq2seq model (or any autoregressive model, or a structured prediction output), CTC models output timesteps as conditionally independent. Hence, everyone uses an RNN LM or n-gram LM or both when retrieving probable sequences from a CTC model (e.g. with beam search).
I guess that's a bit indirect, but these RNNs are essentially learning the 'rules' that actual phrases conform to. It'd definitely be better than trying to hard-code the rules (especially for a language like English!). And the training data is very easy to get: just feed it a few thousand ebooks, the comments section from HN etc.