Package julius

Large vocabulary continuous speech recognition (LVCSR) decoder software

http://julius.sourceforge.jp/

"Julius" is a high-performance, two-pass large vocabulary continuous speech
recognition (LVCSR) decoder software for speech-related researchers and
developers. Based on word N-gram and context-dependent HMM, it can perform
almost real-time decoding on most current PCs in 60k word dictation task.
Major search techniques are fully incorporated such as tree lexicon, N-gram
factoring, cross-word context dependency handling, enveloped beam search,
Gaussian pruning, Gaussian selection, etc. Besides search efficiency, it is
also modularized carefully to be independent from model structures, and
various HMM types are supported such as shared-state triphones and
tied-mixture models, with any number of mixtures, states, or phones.
Standard formats are adopted to cope with other free modeling toolkit such
as HTK, CMU-Cam SLM toolkit, etc.
General Commands (Section 1)
accept_check
accept_check is a tool to check whether a sentence can be accepted or rejected on a grammar (prefix.dfa and prefix.dict). The sentence should be given from...
adinrec
adinrec opens an audio stream, detects an utterance input and store it to a specified file. The utterance detection is done by level and zero-cross thresholds...
adintool
adintool analyzes speech input, finds speech segments skipping silence, and records the detected segments in various ways. It performs speech detection based on...
dfa_determinize
dfa_determinize converts a non-deterministic .dfa file into deterministic DFA. Output to standard output, or file specified by "-o" option. This additional tool...
dfa_minimize
dfa_minimize will convert an .dfa file to an equivalent minimal form. Output to standard output, or to a file specified by "-o" option. On version 3.5.3 and...
generate
This small program randomly generates sentences that are acceptable by the given grammar. .dfa, .dict and .term files are needed to execute. They can be...
generate-ngram
generate-ngram is a tool to generate sentences randomly according to the given N-gram language model. The N-gram model file binary_ngram should be an binary...
gram2sapixml.pl
gram2sapixml.pl converts a recognition grammar file of Julius (.grammar, .voca) to Microsoft SAPI XML grammar format. prefix should be a file name of target...
jclient.pl
This is yet another sample client written in perl. It will connect to Julius running in module mode, receive recognition results from Julius, and cna send...
jcontrol
jcontrol is a simple console program to control julius running on other host via network API. It can send command to Julius, and receive messages from Julius...
julius
julius is a high-performance, multi-purpose, open-source speech recognition engine for researchers and developers. It is capable of performing almost real-time...
mkbingram
mkbingram is a tool to convert N-gram definition file(s) in ARPA standard format to a compact Julius binary format. It will speed up the initial loading time of...
mkbinhmm
mkbinhmm convert an HMM definition file in HTK ascii format into a binary HMM file for Julius. It will greatly speed up the launch process. You can also embed...
mkbinhmmlist
mkbinhmmlist converts a HMMList file to binary format. Since the index trees for lookup are also stored in the binary format, it will speed up the startup of...
mkdfa.pl
mkdfa.pl compiles the Julian format grammar (.grammar and .voca) to Julian native formats (.dfa and .dict). In addition, ".term" will be also generated that...
mkgshmm
mkgshmm converts monophone HMM definition file in HTK format into a special format for Gaussian Mixture Selection (GMS) in Julius. GMS is an algorithm to reduce...
mkss
mkss is a tool to estimate noise spectrum for spectral subtraction on Julius. It reads a few seconds of sound data from microphone input, calculate the average...
nextword
Given a partial (part of) sentence from the end, it outputs the next words allowed in the specified grammar. .dfa, .dict and .term files are needed to execute...