| __A_CELL2__ | Transition arc holding cell |
| __adin__ | A/D-in work area |
| __backtrellis__ | Whole word trellis (aka backtrellis) generated as a result of 1st pass |
| __confnet_cluster__ | Word Cluster for confusion network generation |
| __FSBeam__ | Work area for the first pass |
| __gmm_calc__ | Work area for GMM calculation |
| __gram_list__ | List of grammars to be read at startup |
| __hmmwork__ | Work area and cache for HMM computation |
| __j_plugin_entry__ | Plugin function entry |
| __j_useropt__ | User-defined option |
| __Jconf__ | Configuration parameters (global) |
| __jconf_am__ | Configuration parameters (AM) |
| __jconf_lm__ | Language models (N-gram / DFA), dictionary, and related parameters |
| __jconf_search__ | Search parameters |
| __mfcc_calc__ | Instance for a parameter vector computation |
| __multi_gram__ | Grammar holder |
| __nextword__ | Next word candidate in the 2nd pass |
| __ngram_info__ | Main N-gram structure |
| __node__ | Sentence hypothesis at 2nd pass |
| __Output__ | Recognition result output structure |
| __process_am__ | Instance for an AM |
| __process_lm__ | Instance for a LM |
| __RealBeam__ | Work area for realtime processing of 1st pass |
| __Recog__ | Top level instance for the whole recognition process |
| __recogprocess__ | Instance for a decoding, i.e |
| __sentence__ | Output result structure |
| __sentence_align__ | Alignment result, valid when forced alignment was done |
| __StackDecode__ | Work area for the 2nd pass |
| __trellis_atom__ | Word trellis element that holds survived word ends at each frame on the 1st pass |
| __word_graph__ | Word arc on the word graph |
| _a_cell | Transition arc of HMM state |
| _apatnode | Patricia binary tree node, to search related pointer from string |
| _bmalloc_base | Information of allocated memory block for mybmalloc() |
| _cd_set | Context-dependent HMM set (called "pseudo") for a logical context |
| _dfa_arc | Transition arc of DFA |
| _HMM_logical | Logical HMM to map logical names to physical/pseudo HMM |
| _HTK_HMM_data | Top HMM model, corresponds to "~h" macro in hmmdefs |
| _HTK_HMM_dens | HMM Gaussian density (or mixture) data |
| _HTK_HMM_PDF | HMM mixture PDF for a stream |
| _HTK_HMM_state | HMM state data |
| _HTK_HMM_stream_weight | HMM stream weight definition |
| _HTK_HMM_trans | HMM transition table |
| _HTK_HMM_variance | HMM variance data |
| _patnode | Another patricia binary tree node, to search integer value from string |
| _seg_token | Token definition for viterbi segmentation |
| ACOUSTIC_SPEC | State output probability container on lexicon tree |
| BASEPHONE | Basephone information extracted from hmminfo |
| CD_State_Set | Context-dependent state set, equivalent to HTK_HMM_State, part of pseudo phone |
| CMEAN | Structure to hold sentence sum of MFCC for realtime CMN |
| CMNWork | Work area for real-time CMN |
| DeltaBuf | Cycle buffer for delta computation |
| DFA_INFO | Top structure of a DFA |
| DFA_STATE | State of DFA |
| DS_BUFFER | Down sampling data |
| DS_FILTER | Down sampling filter |
| ENERGYWork | Work area for energy normalization on real time input |
| FBankInfo | Workspace for filterbank analysis |
| GCODEBOOK | Gaussian mixture codebook in tied-mixture model |
| GS_SET | Set of HMM states for Gaussian Mixture Selection |
| HMM | HMM state sequence |
| HMM_basephone | List of all basephone in hmminfo |
| HMM_CDSET_INFO | Top structure to hold all the HMM sets |
| HMM_STATE | HMM State |
| HTK_HMM_INFO | Top HMM structure that holds all the HTK HMM definition |
| HTK_HMM_Options | HMM Option |
| HTK_HMM_StreamInfo | Stream information (although current Julius supports only single stream) |
| HTK_Param | Input speech parameter |
| HTK_Param_Header | Parameter types and extraction conditions |
| LM_PROB_CACHE | LM cache for the 1st pass |
| LMFunc | User LM function entry point |
| LRC_INFO | State output probability data for 1-phone word |
| MFCCWork | Work area for MFCC computation |
| MIXCACHE | A component of per-codebook probability cache while search |
| NGRAM_TUPLE_INFO | N-gram entries for a m-gram (1 <= m <= N) |
| OptionStr | Structure for decoding/encoding parameter type code |
| RC_INFO | State output probability data for head phone of a word |
| s_cell | Element of successor word list for LM factoring computation |
| TERM_INFO | Information of each terminal symbol (=category) |
| TOKEN2 | Token to hold viterbi pass history |
| Value | Mfcc configuration parameter values |
| wchmm_info | Whole lexicon tree structure holding all information |
| wchmm_state | HMM state on tree lexicon |
| WCHMM_WORK | Wchmm-specific work area |
| WORD_INFO | Word dictionary structure to hold vocabulary |
| ZEROCROSS | Work area for zero-cross computation |
1.5.1