deeplearningsprint / eesen Goto Github PK

Eesen is to simplify the existing complicated, expertise-intensive ASR pipeline into a straightforward learning problem. Acoustic modeling in Eesen involves training a single recurrent neural network (RNN) to model the mapping from speech to transcripts. Eesen discards the following elements required by the existing ASR pipeline:

• Hidden Markov models (HMMs)
• Gaussian mixture models (GMMs)
• Decision trees and phonetic questions
• Dictionary, if characters are used as the modeling units
• ...

Eesen was created by Yajie Miao based on the Kaldi toolkit.

Eesen contains 3 key components to enable end-to-end ASR:

• Acoustic Model -- Bi-directional RNNs with LSTM units.
• Training -- Connectionist temporal classification (CTC) as the training objective.
• Decoding -- A principled decoding approach based on Weighted Finite-State Transducers (WFSTs).

• The WFST-based decoding approach can incorporate lexicons and language models into CTC decoding in an effective and efficient way.
• GPU implementation of LSTM model training and CTC learning.
• Multiple utterances are processed in parallel for training speed-up.
• Fully-fledged example setups to demonstrate end-to-end system building, with both phonemes and characters as labels.

Refer to RESULTS under each example setup.

For more informaiton, refer to the following paper(s):

EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding, ASRU 2015.