 addMyPath | Add necessary paths for the ASR toolbox |
| asrPerfEval | asrPerfEval: Performance evaluation of ASR |
| asraOutputXmlRead | asraOutputXmlRead: Read ASRA output xml file |
| cm2labFile | |
| cmRead | cmRead: Read the CM (confidence measure) file generated from Viterbi forced alignment or from human labeling |
| cmWordBgPlot | cmWordBgPlot: Plot background yellow patches for words obtained from a given CM (confidence measure) file |
| dictRead | dictRead: Read a dic file |
| dictSort | dictSort: Sort a dict based on its words |
| dictWrite | dictWrite: Write a dict to a dict file |
| digitConvert4military | digitConvert4military: Convert digits in a text into military pronunciation |
| feaRead | feaRead: Read the feature file generated by hcopy of HTK |
| flv2wav | flv2wav: Convert a flv file to a wav file |
| forwardBackwardAnalysis | |
| getWaveData | GETWAVE Get wave files for given speaker |
| go | |
| goCheckFile | |
| goDemoSa | Demo of assessment of ASRA (automatic speech recognition & assessment) |
| goDemoVc | Demo of ASR of ASRA (automatic speech recognition & assessment) |
| goGenTcpAndFileCopy4ContentInFilename | Generate fea files and the tcp file for ASR training. |
| goWaveAssess4dir | Uses waveAssess.m to generate lab files for a given directory of wave files |
| grammarGen4ks | grammarGen4ks: Generate grammar and net files for keyword spotting with FSD as the filler model |
| hanyu2initialFinal | hanyu2initialFinal: Hanyu syllable to initial and final |
| hanyu2tonalInitialFinal | hanyu2tonalInitialFinal: Hanyu syllable to tonal initial and final |
| isTradChinese | isTradChinese: Check if the given string is traditional Chinese |
| isUnvoicedPhone | isUnvoicedPhone: Return 1 if the given phone is unvoiced |
| lab2pitchedIndex | lab2pitchedIndex: Get pitched index from lab and qiYinFile |
| labRead | labRead: Read the LAB file generated from Viterbi forced alignment or from human labeling |
| labRead0 | labRead: Read a lab file |
| labRead2 | labRead: Read a *.lab file |
| macroRead | macroRead: Read a macro file |
| macroRead_b | macroRead: Read a macro file |
| mlfRead | mlfRead: Read an MLF file |
| mlfRead_old | mlfRead: Read the MLF file generated from Viterbi forced alignment |
| mlfWrite | mlfRead: Write an MLF file |
| netWrite | netWrite: Write a net file |
| pa2pa | pa2pa: PA (phonetic alphabet) to PA conversion (mainly Hanyu vs. Zhuyin) |
| pa2phone | pa2pa: PA (phonetic alphabet) to phone (model) conversion, mainly for Hanyu Pinyin |
| plpRead | plpRead: Read a plp file |
| rank2gbellParam | rank2gbellParam: Return the parameter "a" of a generalized bell function based on a vector of given ranks. |
| saParamSet | ====== Find the path to the executable |
| spRead | SPREAD Read HTK (".SP") sound file. |
| syl2css | syl2css: Find the confusing syllable set (CSS) from a given Mandarin syllable in HanYu PinYin. |
| sylFile2sylFile4sa | sylFile2sylFile4sa: Generate a .syl file (with confusing phones) from a given .syl file for speech assessment |
| sylRead | sylRead: Read a .syl file |
| syls2css | syls2css: Find the confusing syllable set (CSS) from a given Mandarin syllable sequence in HanYu PinYin. |
| text2pa4chinese | text2pa4chinese: Convert a sentence into phonetic alphabets (in Hanyu Pinyin) using maximum matching |
| text2pa4english | text2pa4english: Text (a sentence) to PA (phonetic alphabet) conversion |
| textNormalize4english | textNormalize: English text normalization for pinyin |
| ttt | Demo of assessment of ASRA (automatic speech recognition & assessment) |
| txt2fsmLmFile | txt2fsmLmFile: Conversion from a text file to a LM file for FSM |
| txtEng2netFile | txtEng2netFile: Read an English sentence and convert it to a net file |
| uvBgPlot | cmWordBgPlot: Plot background yellow patches for words obtained from a given CM (confidence measure) file |
| uvCut | uvCut: Find the cut for unvoiced/voiced boundary |
| voiceCommand | waveRecog: Wave assessment which generates an CM (confidence measure) file (and a pitch file, if necessary) from a given wave file and the corresponding text |
| wave2mfccTest | 測試不同的程式所產生的 MFCC 的差異 |
| wave2mfccTest2 | 測試不同的程式所產生的 MFCC 的差異 |
| wave2mlfViaHtk | wave2mlf: Generate an MLF file from a given wav file and corresponding text (by HTK) |
| wave2pitch4pmp | wave2pitch4pmp: Generate a pitch file from a given wave file |
| waveAssess | waveAssess: Wave assessment which generates an CM (confidence measure) file (and a pitch file, if necessary) from a given wave file and the corresponding text |
| waveAssess4dir | waveAssess4dir: Wave Assessment for a directory of wave files(wadParam) |
| waveCmPitchPlot | waveCmPitchPlot: Plot waveform and pitch simultaneously |
| waveCmPlot | waveCmPlot: Generate wave segmentation plot from a wav file and the corresponding CM (confidence measure) file |
| waveDir2fea | waveDir2fea: Convert a directory of a wave files to a directory of feature files |
| wordPlay | wordPlay: Play each word after forced alignment |
| wordQiYinBgPlot | cmWordBgPlot: Plot background yellow patches for words obtained from a given CM (confidence measure) file |
| wpaExtract | wpaExtract: Extract a dictFile to a smaller one which contains words in textFile |
| wpaRead | wpaRead: Read wpa file into a structure |
| wpaRead2 | wpaRead: Read a wpa file |
| wpaWrite | wpaWrite: Write a wpa to a wpa file |
Master index