Let’s Enhance Kaldi, Here are some links along the way. Look like YouTube is progressing a lot during the last couple of years so basically here is just a bunch of random videos creating my favorite playlist to learn all the cool stuff under the Kaldi’s hood.
LattceFasterDecoderLattices: A more complex form of FST‘s, The first version decoders were based on FST’s (like faster-decoder and online decoders). For Minimum Bayesian Risk Calculation Using Lattices will give you a better paved wayfaster-decoder: Old decoder, very simple to understand how decoding process is donelattice-faster-decoder: general decoder, same as faster-decoder but output lattices instead of FSTsDecodableInterface: An interface that connects decoder to the features. decoder uses this Decodable object to pull CMVN features from it.BestPath: An FST that constructed from the Best Path (path with maximum likelihood) in the decoded FST.nBestPath: An FST constructed from the top N Best Path in the decoded FST.GetLinearSymbolSequence: The final step in the recognition process, get a BestPath FST or Lattice and output the recognized words with the path weight. CompactLattices need to be converted using ConvertLatticeStrongly Connected Component: A set that all components are accessible (in two ways) by it’s member.ProcessEmitting that pulls loglikelihood from the decodable objectThanks to this marvelous framework, a trained model is at disposal with WER of absolute zero percent over the 10 minutes of continuous speech file. The final piece to this puzzle would be implementing a semi-online decoding tool using GStreamer. As always useful links for further inspection
gst_caps_to_string(caps)Here I am, pursuing once more the old-fashioned machine learning. I’ll keep it short and write down useful links
