sumom****@users*****
sumom****@users*****
2008年 10月 2日 (木) 17:23:45 JST
Index: julius4/adintool/00readme-ja.txt
diff -u julius4/adintool/00readme-ja.txt:1.2 julius4/adintool/00readme-ja.txt:1.3
--- julius4/adintool/00readme-ja.txt:1.2 Tue Dec 18 23:08:21 2007
+++ julius4/adintool/00readme-ja.txt Thu Oct 2 17:23:45 2008
@@ -1,206 +1,214 @@
+ adintool
+
ADINTOOL(1) ADINTOOL(1)
-NAME
- adintool - audio tool to record/split/send/receive speech data for
- Julius
+–¼‘O
+ adintool
+ - ‰¹º”gŒ`ƒf[ƒ^‚Ì‹L˜^E•ªŠ„E‘—MEŽóMƒc[ƒ‹
-SYNOPSIS
- adintool -in inputdev -out outputdev [options...]
+ŠT—v
+ adintool {-in inputdev} {-out outputdev} [options...]
DESCRIPTION
- adintool ‚ÍC‰¹º”gŒ`ƒf[ƒ^’†‚̉¹º‹æŠÔ‚ÌŒŸo‚¨‚æ‚Ñ‹L˜^‚ð˜A‘±“I‚É s ‚¤
- ƒc[ ƒ‹‚Å‚·D“ü—͉¹º‚ɑ΂µ‚Ä—ëŒð·”‚ÆU•ƒŒƒxƒ‹‚Ɋ¹º‹æŠÔŒŸo‚ð
+ adintool ‚ÍC‰¹º”gŒ`ƒf[ƒ^’†‚̉¹º‹æŠÔ‚ÌŒŸo‚¨‚æ‚Ñ‹L˜^‚ð˜A‘±“I‚És ‚¤
+ ƒc[ƒ‹‚Å‚·D“ü—͉¹º‚ɑ΂µ‚Ä—ëŒð·”‚ÆU•ƒŒƒxƒ‹‚Ɋ¹º‹æŠÔŒŸ o‚ð
’€ŽŸs‚¢C‰¹º‹æŠÔ•”•ª‚ð˜A‘±o—Í‚µ‚Ü‚·D
adintool ‚Í adinrec ‚Ì‚‹@”\”Å‚Å‚·D‰¹ºƒf[ƒ^‚Ì“ü—ÍŒ³‚Æ‚µ‚ÄCƒ}ƒCƒN “ü
- —ÍE ‰¹ º”gŒ`ƒtƒ@ƒCƒ‹E•W€“ü—ÍEƒlƒbƒgƒ[ƒN“ü—Í(adinnet ƒT[ƒo[ƒ‚[
- ƒh)‚ª‘I‘ð‚Å‚«‚Ü‚·D‚Ü‚½Co—Íæ‚Æ‚µ‚ÄC‰¹º”gŒ`ƒtƒ@ƒCƒ‹E•W€o—ÍEƒlƒb
- ƒg ƒ[ƒNo—Í(adinnet ƒNƒ‰ƒCƒAƒ“ƒgƒ‚[ƒh)‚ª‘I‘ð‚Å‚«‚Ü‚·D“Á‚Ƀlƒbƒgƒ[
- ƒNo—Íiadinnet ƒNƒ‰ƒCƒAƒ“ƒgƒ‚[ƒhj‚Å‚ÍC julius ‚Öƒlƒbƒgƒ[ƒNŒo—R ‚Å
- ‰¹º‚ð‘—M‚µ‚ĉ¹º”FŽ¯‚³‚¹‚邱‚Æ‚ª‚Å‚«‚Ü‚·D
-
- “ü —͉¹º‚͉¹º‹æŠÔ‚²‚Æ‚ÉŽ©“®•ªŠ„‚³‚êC’€ŽŸo—Í‚³‚ê‚Ü‚·D‰¹º‹æŠÔ‚ÌØ‚è
- o‚µ‚É‚Í adinrec ‚Æ“¯‚¶Cˆê’莞ŠÔ“à‚Ì—ëŒð·”‚ƃpƒ[iU•ƒŒƒxƒ‹j‚Ì‚µ
- ‚« ‚¢’l‚ð—p‚¢‚Ü‚·D‰¹º‹æŠÔŠJŽn‚Æ“¯Žž‚ɉ¹ºo—Í‚ªŠJŽn‚³‚ê‚Ü‚·Do—Í‚Æ‚µ
- ‚ătƒ@ƒCƒ‹o—Í‚ð‘I‚ñ‚¾ê‡‚ÍC˜A”Ôƒtƒ@ƒCƒ‹–¼‚ÅŒŸo‚³‚ꂽ‹æŠÔ‚²‚Æ‚É•Û ‘¶
- ‚µ‚Ü‚·D
-
- ƒTƒ“ƒvƒŠƒ“ƒOŽü”g”‚Í”CˆÓ‚ÉÝ’è‰Â”\‚Å‚·DŒ`Ž®‚Í 16bit monoral ‚Å‚·D‘‚«
- o‚³‚ê‚éƒf[ƒ^Œ`Ž®‚Í WAV, 16bit, ƒ‚ƒmƒ‰ƒ‹‚Å‚·DŠù‚É“¯‚¶–¼‘O‚̃tƒ@ƒCƒ‹‚ª
- ‘¶Ý‚·‚éꇂÍã‘‚«‚µ‚Ü‚·D
-
-INPUT
- ‰¹º‚ð“Ç‚Ýž‚Þ“ü—̓fƒoƒCƒX‚͈ȉº‚Ì‚¤‚¿‚Ç‚ê‚©‚ðŽw’肵‚Ü‚·D
-
- -in mic
- ƒ}ƒCƒN“ü—ÍiƒfƒtƒHƒ‹ƒgjD
-
- -in file
- ‰¹º”gŒ`ƒtƒ@ƒCƒ‹DŒ`Ž®‚Í RAW (16bit big endian)CWAV(–³ˆ³k)‚È‚Ç
- iƒRƒ“ƒpƒCƒ‹Žž‚ÌÝ’è‚É‚æ‚éjD
- ‚È‚¨C“ü—̓tƒ@ƒCƒ‹–¼‚Í‹N“®Œã‚ÉCƒvƒƒ“ƒvƒg‚ɑ΂µ‚Ä“ü—Í‚·‚éD
-
- -in adinnet
- adinnet ƒT[ƒo[‚Æ‚È‚Á‚ălƒbƒgƒ[ƒNŒo—R‚Å adinnet ƒNƒ‰ƒCƒAƒ“ ƒg
- ‚© ‚特ºƒf[ƒ^‚ðŽó‚¯Žæ‚éD adinnet ƒNƒ‰ƒCƒAƒ“ƒg‚©‚ç‚ÌTCP/IPÚ‘±
- ‚ð‘Ò‚¿CÚ‘±‚ªŠm—§‚µ‚½Œã‚Í adinnet ƒNƒ‰ƒCƒAƒ“ƒg‚©‚特ºƒf[ƒ^ ‚ð
- Žó‚¯Žæ‚éD
- ƒ|[ ƒg ”Ô†‚̃fƒtƒHƒ‹ƒg‚Í 5530 ‚Å‚ ‚éD‚±‚ê‚̓IƒvƒVƒ‡ƒ“ "-port"
- ‚Å•ÏX‰Â”\D
-
- -in netaudio
- (ƒTƒ|[ƒg‚³‚ê‚Ä‚¢‚ê‚Îj‰¹ºƒf[ƒ^‚ðNetaudio/DatLinkƒT[ƒo[‚© ‚ç
- Žó ‚¯Žæ‚éDƒT[ƒo‚̃zƒXƒg–¼‚ƃ†ƒjƒbƒg–¼‚ð "-NA host:unit" ‚ÅŽw’è
- ‚·‚é•K—v‚ª‚ ‚éD
-
- -in stdin
- •W€“ü—ÍD‰¹ºƒf[ƒ^Œ`Ž®‚Í RAW, WAV ‚Ì‚ÝD
-
-OUTPUT
- ŒŸo‚µ‚½‰¹º‹æŠÔ‚̉¹ºƒf[ƒ^‚ð‘‚«o‚·o—̓fƒoƒCƒX‚Æ‚µ‚ÄCˆÈ‰º‚Ì‚¤‚¿ ‚Ç
- ‚ê‚©‚ðŽw’肵‚Ü‚·D
-
- -out file
- ƒtƒ@ ƒC ƒ‹ ‚Ö o—Í‚·‚éDo—̓tƒ@ƒCƒ‹–¼‚͕ʂ̃IƒvƒVƒ‡ƒ“"-filename
- foobar" ‚ÌŒ`‚Å—^‚¦‚éDŽÀÛ‚É‚Í "foobar.0000" , "foobar.0001" ...
- ‚Ì ‚悤‚É‹æŠÔ‚²‚Æ‚ÉCŽw’肵‚½–¼‘O‚Ì––”ö‚É4Œ…‚ÌID‚ð‚‚¯‚½–¼‘O‚Å‹L
- ˜^‚³‚ê‚È‚éD ID ‚Í 0 ‚ð‰Šú’l‚Æ‚µ‚ÄC‰¹º‹æŠÔŒŸo‚²‚Æ‚É‚P‘‰Á ‚·
- ‚éD ‰ Šú’l‚̓IƒvƒVƒ‡ƒ“ "-startid" ‚Å•ÏX‰Â”\‚Å‚ ‚éD‚Ü‚½Co—Í
- ƒtƒ@ƒCƒ‹Œ`Ž®‚Í 16bit WAV Œ`Ž®‚Å‚ ‚éD RAW Œ`Ž®‚Åo—Í ‚· ‚é ‚É ‚Í
- "-raw" ƒIƒvƒVƒ‡ƒ“‚ðŽw’è‚·‚éD
-
- -out adinnet
- adinnet ƒNƒ‰ƒCƒAƒ“ƒg‚Æ‚È‚Á‚ÄCƒlƒbƒgƒ[ƒNŒo—R‚Å adinnet ƒT[ƒo
- ‚Ö‰¹ºƒf[ƒ^‚ð‘—‚éD“ü—Í‚ÌŽž‚Æ‚Í‹t‚ÉC adintool ‚Í adinnet ƒN ƒ‰
- ƒC ƒA ƒ“ ƒg ‚Æ‚È‚èCadinnet ƒT[ƒo[‚ÖÚ‘±ŒãC‰¹ºƒf[ƒ^‚ð‘—M‚·
- ‚éDadinnet ƒT[ƒo[‚Æ‚µ‚Ä‚ÍC adintool ‚¨‚æ‚Ñ Julius ‚Ìadinnet
- “ü—Í‚ª‹“‚°‚ç‚ê‚éD
- "-server" ‚Å‘—Mæ‚ÌadinnetƒT[ƒo‚̃zƒXƒg–¼‚ðŽw’è‚·‚éD‚Ü‚½ƒ|[
- ƒg”Ô†‚̃fƒtƒHƒ‹ƒg‚Í 5530 ‚Å‚ ‚éD‚±‚ê‚̓IƒvƒVƒ‡ƒ“ "-port" ‚Å •Ï
- X‰Â”\D
-
- -out stdout
- •W € o—Í‚Öo—Í‚·‚éDŒ`Ž®‚Í RAW, 16bit signed (big endian) ‚Å‚
- ‚éD
-
+ —ÍE ‰¹º”gŒ`ƒtƒ@ƒCƒ‹E•W€“ü—ÍEƒlƒbƒgƒ[ƒN“ü—Í(adinnet ƒT[ƒo[ ƒ‚[
+ ƒh)‚ª‘I‘ð‚Å‚«‚Ü‚·DJulius ‚Ì -input ƒIƒvƒVƒ‡ƒ“‚à Žg—p‰Â”\‚ÅCƒvƒ‰ƒOƒCƒ“
+ “ü—Í‚à‘I‘ð‚Å‚«‚Ü‚·D
+
+ o—Íæ‚Æ‚µ‚ÄC‰¹º”gŒ`ƒtƒ@ƒCƒ‹E•W€o—ÍEƒlƒbƒgƒ[ƒNo—Í(adinnet ƒN
+ ƒ‰ƒCƒAƒ“ƒgƒ‚[ƒh)‚ª‘I‘ð‚Å‚«‚Ü‚·D“Á‚Ƀlƒbƒgƒ[ƒNo—Íiadinnet ƒNƒ‰ƒC
+ ƒAƒ“ƒgƒ‚[ƒhj‚Å‚ÍC julius ‚Öƒlƒbƒgƒ[ƒNŒo—R‚ʼn¹º‚ð‘—M‚µ‚ĉ¹º”FŽ¯
+ ‚³‚¹‚邱‚Æ‚ª‚Å‚«‚Ü‚·D
+
+ “ü—͉¹º‚͉¹º‹æŠÔ‚²‚Æ‚ÉŽ©“®•ªŠ„‚³‚êC’€ŽŸo—Í‚³‚ê‚Ü‚·D‰¹º‹æŠÔ‚ÌØ ‚è
+ o‚µ‚É‚Í adinrec ‚Æ“¯‚¶Cˆê’莞ŠÔ“à‚Ì—ëŒð·”‚ƃpƒ[iU•ƒŒƒxƒ‹j ‚Ì
+ ‚µ‚«‚¢’l‚ð—p‚¢‚Ü‚·D‰¹º‹æŠÔŠJŽn‚Æ“¯Žž‚ɉ¹ºo—Í‚ªŠJŽn‚³‚ê‚Ü‚·Do —Í‚Æ
+ ‚µ‚ătƒ@ƒCƒ‹o—Í‚ð‘I‚ñ‚¾ê‡‚ÍC˜A”Ôƒtƒ@ƒCƒ‹–¼‚ÅŒŸo‚³‚ꂽ‹æŠÔ‚²‚Æ ‚É•Û
+ ‘¶‚µ‚Ü‚·D
+
+ ƒTƒ“ƒvƒŠƒ“ƒOŽü”g”‚Í”CˆÓ‚ÉÝ’è‰Â”\‚Å‚·D˜^‰¹Œ`Ž®‚Í 16bit, 1 channel
+ ‚ÅC‘‚«o‚³‚ê‚éƒtƒ@ƒCƒ‹Œ`Ž®‚Í Microsoft WAV Œ`Ž®‚Å‚·D Šù‚É“¯‚¶–¼‘O‚Ì
+ ƒtƒ@ƒCƒ‹‚ª‘¶Ý‚·‚éꇂÍã‘‚«‚³‚ê‚Ü‚·D
OPTIONS
- -server host[,host...]
- "-out adinnet" ‚Å‘—M‚·‚éƒT[ƒo‚̃zƒXƒg–¼‚ðŽw’è‚·‚éDƒRƒ“ƒ}‹æ Ø
- ‚è‚Å•¡”‚̃T[ƒo‚ðŽw’è‰Â”\D
-
- -port num[,host...]
- "-out adinnet" ‚Å‘—M‚·‚éƒT[ƒo‚̃|[ƒg”Ô†D•¡”ƒT[ƒoŽg—pŽž‚Í
- ƒRƒ“ƒ}‹æØ‚è‚Å "-server"‚ɑΉž‚³‚¹‚Ä‘S‚Ă̔Ԇ‚ðŽw’è‚·‚é ‚± ‚ÆD
- (default: 5530)
-
- -nosegment
- “ü—͉¹º‚ɑ΂µ‚ĉ¹º‹æŠÔ‚ÌŒŸo‚ðs‚킸C‚»‚Ì‚Ü‚Üo—Í‚ÖƒŠƒ_ƒCƒŒƒN
- ƒg‚·‚éDƒtƒ@ƒCƒ‹o—Í‚Ìê‡Cƒtƒ@ƒCƒ‹–¼‚Ì––”ö‚É4Œ…‚ÌID‚Í•t—^‚³ ‚ê
- ‚È‚‚È‚éD
-
- -oneshot
- “ü—ÍŠJŽnŒãCˆê”Ôʼn‚Ì‚P‰¹º‹æŠÔ‚Ì‚Ý‚ð‘—MŒãCI—¹‚·‚éD
-
- -freq threshold
- ƒTƒ“ƒvƒŠƒ“ƒOŽü”g”D’PˆÊ‚Í Hz (default: 16000)
-
- -48 48kHzƒTƒ“ƒvƒŠƒ“ƒOŒãC16kHz‚Ƀ_ƒEƒ“ƒTƒ“ƒvƒŠƒ“ƒO‚·‚éD
-
- -lv threslevel
- ”gŒ`‚ÌU•ƒŒƒxƒ‹‚Ì‚µ‚«‚¢’l (0 - 32767)D(default: 2000)D
-
- -zc zerocrossnum
- ‚P•b‚ ‚½‚è‚Ì—ëŒð·”‚Ì‚µ‚«‚¢’l (default: 60)
-
- -headmargin msec
- ‰¹º‹æŠÔŠJŽn•”‚Ì’¼‘O‚̃}[ƒWƒ“D’PˆÊ‚̓~ƒŠ•b (default: 400)
-
- -tailmargin msec
- ‰¹º‹æŠÔI—¹•”‚Ì’¼Œã‚̃}[ƒWƒ“D’PˆÊ‚̓~ƒŠ•b (default: 400)
-
- -nostrip
- –³ Œø‚È 0 ƒTƒ“ƒvƒ‹‚ÌŽ©“®œ‹Ž‚ðs‚í‚È‚¢‚悤‚É‚·‚éDƒfƒtƒHƒ‹ƒg‚ÍŽ©
- “®œ‹Ž‚ðs‚¤D
-
- -zmean DC¬•ªœ‹Ž‚ðs‚¤D
+ Julius ‚Ì‘S‚ẴIƒvƒVƒ‡ƒ“‚ªŽw’è‰Â”\‚Å‚ ‚éDŽw’肳‚ꂽ‚à‚Ì‚Ì‚¤‚¿C ‰¹º
+ “ü—Í‚ÉŠÖŒW‚·‚éƒIƒvƒVƒ‡ƒ“‚݈̂µ‚í‚ê‚éDˆÈ‰º‚ÉCadintool ‚Ì ƒIƒvƒVƒ‡ƒ“C
+ ‚¨‚æ‚Ñ—LŒø‚È Julius ƒIƒvƒVƒ‡ƒ“‚ð‰ðà‚·‚éD
+
+ adintool specific options
+ -freq Hz
+ ‰¹º‚̃Tƒ“ƒvƒŠƒ“ƒOŽü”g” (Hz) ‚ðŽw’è‚·‚éD(default: 16,000)
+
+ -in inputdev
+ ‰¹º‚ð“Ç‚Ýž‚Þ“ü—̓fƒoƒCƒX‚ðŽw’è‚·‚éD"mic" ‚Ń}ƒCƒN“ü—ÍC "file" ‚Å
+ ƒtƒ@ƒCƒ‹“ü—Í, "stdin" ‚Å•W€“ü—Í‚©‚特º‚ð“Ç‚Ýž‚ÞD ƒtƒ@ƒCƒ‹“ü—Í‚Ì
+ ê‡Cƒtƒ@ƒCƒ‹–¼‚Í‹N“®Œã‚Éo‚Ä‚‚éƒvƒƒ“ƒvƒg‚É‘Î ‚µ‚ÄŽw’è‚·‚éD‚Ü
+ ‚½C"adinnet" ‚Å adintool ‚Í adinnet ƒT[ƒo[ ‚Æ‚È‚èCadinnet ƒNƒ‰ƒC
+ ƒAƒ“ƒg‚©‚特ºƒf[ƒ^‚ð tcp/ip Œo—R‚Å Žó‚¯Žæ‚éDƒ|[ƒg”Ô†‚Í 5530 ‚Å
+ ‚ ‚éi"-inport" ‚Å•ÏX‰Â”\jD
+
+ “ü—̓fƒoƒCƒX‚ÍC‚»‚Ì‚Ù‚© Julius ‚Ì "-input" ƒIƒvƒVƒ‡ƒ“‚Å‚àŽw’è‰Â”\
+ ‚Å‚ ‚éD‚»‚Ìê‡Cƒvƒ‰ƒOƒCƒ“‚©‚ç‚Ì“ü—Í‚à‰Â”\‚Å‚ ‚éD
+
+ -out outputdev
+ ‰¹º‚ðo—Í‚·‚éƒfƒoƒCƒX‚ðŽw’è‚·‚éD"file" ‚Ńtƒ@ƒCƒ‹o—ÍC stdout ‚Å
+ •W€o—Í‚Öo—Í‚·‚éDƒtƒ@ƒCƒ‹‚Ìê‡Co—̓tƒ@ƒCƒ‹–¼‚Í ƒIƒvƒVƒ‡ƒ“
+ "-filename" ‚Å—^‚¦‚éDo—̓tƒ@ƒCƒ‹ Œ`Ž®‚Í 16bit WAV Œ`Ž®‚Å‚ ‚éD ‚Ü
+ ‚½C"adinnet" ‚Å adintool ‚Í adinnet ƒNƒ‰ƒCƒAƒ“ƒg ‚Æ‚È‚èCadinnet
+ ƒT[ƒo‚ÖŽæ‚èž‚ñ‚¾‰¹ºƒf[ƒ^‚ð tcp/ip Œo—R‚Å ‘—M‚Å‚«‚éD‘—MæƒzƒX
+ ƒg‚Í "-server" ‚ÅŽw’è‚·‚éD ƒ|[ƒg”Ô†‚Í 5530 ‚Å‚ ‚éi"-port" ‚Å•ÏX
+ ‰Â”\jD
+
+ -inport num
+ “ü—Í‚ª adinnet ‚Ìê‡ (-in adinnet)CÚ‘±‚ðŽó‚¯‚éƒ|[ƒg”Ô† ‚ðŽw’è‚·
+ ‚éDŽw’肵‚È‚¢ê‡‚̃fƒtƒHƒ‹ƒg‚Í 5530 ‚Å‚ ‚éD
+
+ -server [host] [,host...]
+ o—Í‚ª adinnet ‚Ìê‡ (-out adinnet)C‘—Mæ‚̃T[ƒo–¼‚ðŽw’è‚·‚éD
+ •¡”‚ ‚éꇂÍCƒJƒ“ƒ}‚Å‹æØ‚Á‚ÄŽw’è‚·‚éD
+
+ -port [num] [,num...]
+ o—Í‚ª adinnet ‚Ìê‡ (-out adinnet)C‘—Mæ‚ÌŠeƒT[ƒo‚̃|[ƒg”Ô†
+ ‚ðŽw’è‚·‚éDŽw’肵‚È‚¢ê‡‚̃fƒtƒHƒ‹ƒg‚Í 5530 ‚Å‚ ‚éD -server ‚Å•¡
+ ”‚̃T[ƒo‚ðŽw’肵‚Ä‚¢‚éê‡C ‘S‚Ăɂ‚¢‚Ä–¾Ž¦“I‚Ƀ|[ƒg”Ô†‚ðŽw’è
+ ‚·‚é•K—v‚ª‚ ‚éD
+
+ -filename file
+ ƒtƒ@ƒCƒ‹o—Í (-out file) ŽžCo—̓tƒ@ƒCƒ‹–¼‚ð —^‚¦‚éDƒfƒtƒHƒ‹ƒg‚Å
+ ‚ÍCŒŸo‚³‚ꂽ‰¹º‹æŠÔŒŸo‚²‚Æ‚ÉC "file.0000.wav" , "file.0001.wav"
+ ... ‚̂悤‚É‹æŠÔ‚²‚ƂɘA”Ô‚Å ‹L˜^‚³‚ê‚éD”Ô†‚̉Šú’l‚Í 0 ‚Å‚ ‚é
+ i-startid‚Å •ÏX‰Â”\jD‚È‚¨CƒIƒvƒVƒ‡ƒ“ -oneshot Žw’莞‚Í Å‰‚Ì‹æ
+ ŠÔ‚¾‚¯‚ª "file" ‚Ì–¼‘O‚Å•Û‘¶‚³‚ê‚éD
+
+ -startid number
+ ƒtƒ@ƒCƒ‹o—ÍŽžC‹L˜^‚ðŠJŽn‚·‚é˜A”Ô”Ô†‚̉Šú’l‚ðŽw’è‚·‚éDi ƒfƒtƒH
+ ƒ‹ƒgF0j
+
+ -oneshot
+ ʼn‚̉¹º‹æŠÔ‚ªI—¹‚µ‚½‚çI—¹‚·‚éD
+
+ -nosegment
+ “ü—͉¹º‚̉¹º‹æŠÔŒŸoi–³‰¹‚É‚æ‚é‹æØ‚è‚Æ–³‰¹‹æŠÔ‚̃XƒLƒbƒvj‚ð s
+ ‚í‚È‚¢D
+
+ -raw
+ RAWƒtƒ@ƒCƒ‹Œ`Ž®‚Åo—Í‚·‚éD
+
+ -autopause
+ o—Í‚ª adinnet ‚Ìê‡i-out adinnetjC‰¹º‹æŠÔ‚ªI—¹‚·‚邽‚Ñ ‚É“ü—Í
+ ’âŽ~E“®ì’âŽ~ó‘ԂɈÚs‚·‚éDo—Íæ‚Ì adinnet ƒT[ƒo‚© ‚ç“®ìÄŠJM
+ †‚ª‚‚é‚Ɖ¹º“ü—Í‚ðÄŠJ‚·‚éD
+
+ -loosesync
+ o—Í‚ª adinnet i-out adinnetj‚Å•¡”‚Ìo—ÍæƒT[ƒo‚Öo—Í‚µ‚Ä‚¢‚é ê
+ ‡C“®ì’âŽ~ó‘Ô‚©‚ç“®ìÄŠJM†‚É‚æ‚Á‚Ä“®ì‚ðÄŠJ‚·‚éÛCadintool
+ ‚Í ‚·‚ׂẴT[ƒo‚©‚ç“®ìÄŠJM†‚ðŽó‚¯‚é‚Ü‚Å“®ì‚ðÄŠJ‚µ‚È‚¢D ‚±‚Ì
+ ƒIƒvƒVƒ‡ƒ“‚ðŽw’è‚·‚é‚ÆC‚È‚‚Æ‚à‚P‚‚̃T[ƒo‚©‚çÄŠJM† ‚ª‚‚ê‚Î
+ “®ì‚ðÄŠJ‚·‚é‚悤‚É‚È‚éD
+
+ -rewind msec
+ “ü—Í‚ªƒ}ƒCƒN‚Ì‚Æ‚«C’âŽ~ó‘Ô‚©‚ç“®ì‚ðÄŠJ‚·‚é‚Æ‚«C’âŽ~’†‚©‚ç Ž‘±
+ ‚µ‚ĉ¹º“ü—Í’†‚¾‚Á‚½ê‡CŽw’肳‚ꂽƒ~ƒŠ•b•ª‚¾‚¯‚³‚©‚Ì‚Ú‚Á‚Ä ˜^‰¹‚ð
+ ŠJŽn‚·‚éD
+
+ Concerning Julius options
+ -input {mic|rawfile|adinnet|stdin|netaudio|esd|alsa|oss}
+ ‰¹º“ü—̓\[ƒX‚ð‘I‘ð‚·‚éD"-in" ‚Ì‘ã‚í‚è‚É‚±‚¿‚ç‚ðŽg‚¤‚±‚Æ‚à ‚Å‚«‚é
+ iÅŒã‚ÉŽw’肵‚½‚Ù‚¤‚ª—D悳‚ê‚éjDesd ‚âƒvƒ‰ƒOƒCƒ““ü—Í‚ª Žw’è‰Â”\
+ ‚Å‚ ‚éD
+
+ -lv thres
+ U•ƒŒƒxƒ‹‚Ì‚µ‚«‚¢’lD’l‚Í 0 ‚©‚ç 32767 ‚͈̔͂Ŏw’è‚·‚éD (default:
+ 2000)
+
+ -zc thres
+ —ëŒð·”‚Ì‚µ‚«‚¢’lD’l‚Í‚P•b‚ ‚½‚è‚̌𷔂Ŏw’è‚·‚éD (default: 60)
+
+ -headmargin msec
+ ‰¹º‹æŠÔŠJŽn•”‚̃}[ƒWƒ“D’PˆÊ‚̓~ƒŠ•bD (default: 300)
+
+ -tailmargin msec
+ ‰¹º‹æŠÔI—¹•”‚̃}[ƒWƒ“D’PˆÊ‚̓~ƒŠ•bD (default: 400)
+
+ -zmean
+ “ü—͉¹ºƒXƒgƒŠ[ƒ€‚ɑ΂µ‚Ä’¼—¬¬•ªœ‹Ž‚ðs‚¤D‘S‚Ẳ¹ºˆ—‚Ì ‚Ì‘O
+ ’i‚Æ‚µ‚Ĉ—‚³‚ê‚éD
+
+ -smpFreq Hz
+ ‰¹º‚̃Tƒ“ƒvƒŠƒ“ƒOŽü”g” (Hz) ‚ðŽw’è‚·‚éD(default: 16,000)
+
+ -48
+ 48kHz‚Å“ü—Í‚ðs‚¢C16kHz‚Ƀ_ƒEƒ“ƒTƒ“ƒvƒŠƒ“ƒO‚·‚éD ‚±‚ê‚Í 16kHz ‚̃‚
+ ƒfƒ‹‚ðŽg—p‚µ‚Ä‚¢‚é‚Æ‚«‚Ì‚Ý—LŒø‚Å‚ ‚éD ƒ_ƒEƒ“ƒ_ƒ“ƒvƒŠƒ“ƒO‚Ì“à•”‹@”\
+ ‚Í sptk ‚©‚ç ˆÚA‚³‚ꂽD (Rev. 4.0)
+
+ -NA devicename
+ DatLink ƒT[ƒo‚̃fƒoƒCƒX–¼ (-input netaudio).
+
+ -adport port_number
+
+ -input adinnet Žg—pŽžCÚ‘±‚ðŽó‚¯•t‚¯‚é adinnet ‚̃{[ƒg”Ô†‚ðŽw’è‚·
+ ‚éD(default: 5530)
+
+ -nostrip
+ ‰¹ºŽæ‚èž‚ÝŽžCƒfƒoƒCƒX‚âƒtƒ@ƒCƒ‹‚É‚æ‚Á‚Ä‚ÍC‰¹º”gŒ`’†‚ÉU• ‚ª
+ "0" ‚Æ‚È‚éƒtƒŒ[ƒ€‚ª‘¶Ý‚·‚邱‚Æ‚ª‚ ‚éDJulius ‚Í’ÊíC‰¹º “ü—Í‚ÉŠÜ
+ ‚Ü‚ê‚é‚»‚̂悤‚ȃtƒŒ[ƒ€‚𜋎‚·‚éD‚±‚Ì—ëƒTƒ“ƒvƒ‹œ‹Ž‚ª ‚¤‚Ü‚“®‚©
+ ‚È‚¢ê‡C‚±‚̃IƒvƒVƒ‡ƒ“‚ðŽw’è‚·‚邱‚Æ‚ÅŽ©“®Á‹Ž‚ð –³Œø‰»‚·‚邱‚Æ‚ª
+ ‚Å‚«‚éD
+
+ -C jconffile
+ jconfÝ’èƒtƒ@ƒCƒ‹‚ð“Ç‚Ýž‚ÞDƒtƒ@ƒCƒ‹‚Ì“à—e‚ª‚±‚ÌꊂɓWŠJ‚³‚ê‚éD
+
+ -plugindir dirlist
+ ƒvƒ‰ƒOƒCƒ“‚ð“Ç‚Ýž‚ÞƒfƒBƒŒƒNƒgƒŠ‚ðŽw’è‚·‚éD•¡”‚Ìê‡‚Í ƒRƒƒ“‚Å‹æ
+ Ø‚Á‚Ä•À‚ׂĎw’è‚·‚éD
+
+ENVIRONMENT VARIABLES
+ ALSADEV
+ (ƒ}ƒCƒN“ü—Í‚Å alsa ƒfƒoƒCƒXŽg—pŽž) ˜^‰¹ƒfƒoƒCƒX–¼‚ðŽw’è‚·‚éD Žw’肪
+ ‚È‚¢ê‡‚Í "default"D
+
+ AUDIODEV
+ (ƒ}ƒCƒN“ü—Í‚Å oss ƒfƒoƒCƒXŽg—pŽž) ˜^‰¹ƒfƒoƒCƒX–¼‚ðŽw’è‚·‚éD Žw’肪
+ ‚È‚¢ê‡‚Í "/dev/dsp"D
+
+ LATENCY_MSEC
+ Linux (alsa/oss) ‚¨‚æ‚Ñ Windows ‚ÅCƒ}ƒCƒN“ü—ÍŽž‚Ì’x‰„ŽžŠÔ‚ðƒ~ ƒŠ•b
+ ’PˆÊ‚ÅŽw’è‚·‚éD’Z‚¢’l‚ðÝ’è‚·‚邱‚Æ‚Å“ü—Í’x‰„‚𬂳‚‚Å‚« ‚邪CCPU
+ ‚Ì•‰‰×‚ª‘å‚«‚‚È‚èC‚Ü‚½ŠÂ‹«‚É‚æ‚Á‚Ă̓vƒƒZƒX‚âOS‚Ì ‹““®‚ª•sˆÀ’è‚É
+ ‚Ȃ邱‚Æ‚ª‚ ‚éDÅ“K‚È’l‚ÍOS ‚âƒfƒoƒCƒX‚É‘å‚«‚ ˆË‘¶‚·‚éDƒfƒtƒHƒ‹ƒg
+ ’l‚Í“®ìŠÂ‹«‚Ɉˑ¶‚·‚éD
- -raw ƒtƒ@ƒCƒ‹o—ÍŒ`Ž®‚ð RAW, 16bit signed (big endian) ‚É‚·‚éDƒfƒtƒH
- ƒ‹ƒg‚Í WAV Œ`Ž®‚Å‚ ‚éD
-
- -autopause
- “ü—ÍI—¹‚²‚Æ‚ÉŽ©“®“I‚É pause ó‘Ô‚É“ü‚éD
-
- -loosesync
- •¡ ”ƒT[ƒoÚ‘±ŽžC•¡”ƒT[ƒo‚©‚ç‚Ì pause ‚â resume ƒRƒ}ƒ“ƒh‚É‘Î
- ‚µ‚ÄŒµ–§‚È“¯Šú‚ðs‚í‚È‚¢‚悤‚É‚·‚éD
-
- -rewind msec
- ’ÊíCadintool ‚Í pause ’†‚Ì“ü—͂𖳎‹‚·‚éD‚±‚Ì‚½‚ßCpause’† ‚É
- “ü —Í ‚ª ŠJ Žn ‚³ ‚êC‚»‚Ì“ü—Í‚ªI—¹‚·‚é‘O‚ɃT[ƒoƒRƒ}ƒ“ƒh‚É‚æ‚è
- resume ‚µ‚½‚Æ‚«‚É‹É’[‚É’Z‚¢‰¹ºƒtƒ‰ƒOƒƒ“ƒg‚ªŒŸo‚³‚ê‚邱‚Æ‚Æ ‚È
- ‚éD‚±‚̃IƒvƒVƒ‡ƒ“‚ðŽw’è‚·‚邱‚Æ‚ÅCresumeŽž‚ɉ¹º“ü—Í’†‚Ìê‡C
- “ü—Í‚ð resume Žž“_‚©‚çŽw’肵‚½’·‚³‚¾‚¯‘k‚Á‚Ä‘—M‚·‚éD
-
-EXAMPLE
+EXAMPLES
ƒ}ƒCƒN‚©‚ç‚̉¹º“ü—Í‚ðC”˜b‚²‚Æ‚É "data.0000.wav" ‚©‚燂ɋL˜^‚·‚éF
-
- % adintool -in mic -out file -filename data
-
- ‹‘å‚ÈŽû˜^‰¹ºƒtƒ@ƒCƒ‹ "foobar.raw"‚ð‰¹º‹æŠÔ‚²‚Æ ‚É "foobar.1500.wav"
- "foobar.1501.wav" ... ‚É•ªŠ„‚·‚éF
-
- % adintool -in file -out file -filename foobar
- -startid 1500
- (‹N“®Œãƒvƒƒ“ƒvƒg‚ɑ΂µ‚ătƒ@ƒCƒ‹–¼‚ð“ü—Í)
- enter filename->foobar.raw
-
+ ‹‘å‚ÈŽû˜^‰¹ºƒtƒ@ƒCƒ‹ "foobar.raw" ‚ðC‰¹º‹æŠÔ‚²‚Æ‚É
+ "foobar.1500.wav" "foobar.1501.wav" ... ‚É•ªŠ„‚·‚éF
ƒlƒbƒgƒ[ƒNŒo—R‚ʼn¹ºƒtƒ@ƒCƒ‹‚ð“]‘—‚·‚é(‹æŠÔŒŸo‚È‚µ)F
-
- [ŽóM‘¤]
- % adintool -in adinnet -out file -nosegment
- [‘—M‘¤]
- % adintool -in file -out adinnet -server hostname
- -nosegment
-
- ƒ}ƒCƒN‚©‚ç‚Ì“ü—͉¹º‚ð•ÊƒT[ƒo[‚Ì Julius ‚É‘—‚éF
-
- (1) “ü—̓f[ƒ^‚ð‘S‚Ä‘—M‚µCJulius‘¤‚Å‹æŠÔŒŸoE”FŽ¯F
-
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
- [adintool]
- % adintool -in mic -out adinnet -server hostname
- -nosegment
-
- (2) “ü—̓f[ƒ^‚̓Nƒ‰ƒCƒAƒ“ƒg(adintool)‘¤‚Å‹æŠÔŒŸo‚µCŒŸo‚µ‚½‹æŠÔ‚¾‚¯
- ‚ð‡‚É Julius ‚Ö‘—ME”FŽ¯F
-
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
- [adintool]
- % adintool -in mic -out adinnet -server hostname
+ ƒ}ƒCƒN‚©‚ç‚Ì“ü—͉¹º‚ð Julius ‚Ö‘—M‚µ‚Ä”FŽ¯F
SEE ALSO
- julius(1), adinrec(1)
-
-BUGS
- ƒoƒO•ñE–â‚¢‡‚킹EƒRƒƒ“ƒg ‚È ‚Ç ‚Í julius-info at lists.source-
- forge.jp ‚Ü‚Å‚¨Šè‚¢‚µ‚Ü‚·D
+ julius ( 1 ) ,
+ adinrec ( 1 )
COPYRIGHT
- Copyright (c) 1991-2006 ‹ž“s‘åŠw ‰ÍŒ´Œ¤‹†Žº
- Copyright (c) 2000-2005 “Þ—Çæ’[‰ÈŠw‹Zp‘åŠw‰@‘åŠw Ž–쌤‹†Žº
- Copyright (c) 2005-2006 –¼ŒÃ‰®H‹Æ‘åŠw JuliusŠJ”ƒ`[ƒ€
+ Copyright (c) 1991-2008 ‹ž“s‘åŠw ‰ÍŒ´Œ¤‹†Žº
+
+ Copyright (c) 1997-2000 î•ñˆ—U‹»Ž–‹Æ‹¦‰ï(IPA)
+
+ Copyright (c) 2000-2008 “Þ—Çæ’[‰ÈŠw‹Zp‘åŠw‰@‘åŠw Ž–쌤‹†Žº
-AUTHORS
- —› WL (–¼ŒÃ‰®H‹Æ‘åŠw) ‚ªŽÀ‘•‚µ‚Ü‚µ‚½D
+ Copyright (c) 2005-2008 –¼ŒÃ‰®H‹Æ‘åŠw JuliusŠJ”ƒ`[ƒ€
LICENSE
Julius ‚ÌŽg—p‹–‘ø‚É€‚¶‚Ü‚·D
-4.3 Berkeley Distribution LOCAL ADINTOOL(1)
+ 10/02/2008 ADINTOOL(1)
Index: julius4/adintool/00readme.txt
diff -u julius4/adintool/00readme.txt:1.2 julius4/adintool/00readme.txt:1.3
--- julius4/adintool/00readme.txt:1.2 Tue Dec 18 23:08:21 2007
+++ julius4/adintool/00readme.txt Thu Oct 2 17:23:45 2008
@@ -1,206 +1,214 @@
+ adintool
+
ADINTOOL(1) ADINTOOL(1)
NAME
- adintool - audio tool to record/split/send/receive speech data for
- Julius
+ adintool
+ - a tool to record / split / send / receive audio streams
SYNOPSIS
- adintool -in inputdev -out outputdev [options...]
+ adintool {-in inputdev} {-out outputdev} [options...]
DESCRIPTION
adintool analyzes speech input, finds speech segments skipping silence,
- and records the detected segments in various ways. It performs speech
- detection based on zerocross number and power (level), and records the
+ and records the detected segments in various ways. It performs speech
+ detection based on zerocross number and power (level), and records the
detected parts to files or other output devices sucessively.
- adintool is a highly-functioned version of adinrec. The supported
- input device are: microphone input, a speech file, standard tty input,
- and network socket (called adin-net server mode). The speech segments
- are saved to output devices: speech files, standard tty output, and
- network socket (called adin-net client mode). For example, you can
- record the incoming speech segments to files with successively-numbered
- suffixes, or send them to speech recognition engine julius to recognize
- them.
-
- The output is not buffered: the receiver can get speech data with only
- a slight delay after a speech starts. The speech detection algorithm
- is as same as that of adinrec.
-
- Output format is WAV, 16bit (signed short), monoral. If the file
- already exist, it will be overridden.
-
-INPUT
- The input device should be specified by one of the following options:
-
- -in mic
- Microphone input (default)
- -in file
- Speech data file. Supported format is RAW (16bit big endian)
- and WAV (no compression) etc (depending on the compilation time
- setting).
- The input file name should be given later: prompt will appear
- after startup.
-
- -in adinnet
- Make adintool "adinnet server", waiting for connection from
- adinnet client and receiving speech data from there via tcp/ip
- socket.
- Default port number is 5530, which can be altered by option
- "-port".
-
- -in netaudio
- If supported, get input data from NetAudio/Datlink server. Host
- and unit name should be given with "-NA host:unit" option.
-
- -in stdin
- Read speech data from standard tty input. Only RAW and WAV for-
- mat is supported.
-
-OUTPUT
- Specify one of these below to select an output device which the
- detected speech segments are going to written to.
-
- -out file
- Output to files. The base filename should be given by option
- like "-filename foobar". Actually, the detected segments are
- recorded in separate files such as "foobar.0000", "foobar.0001"
- and so on. The four-digit ID begin with 0. This initial value
- can be set explicitly by option "-startid". The output format
- is WAV, 16bit signed. This can be changed by "-raw" option.
-
- -out adinnet
- Make adintool "adinnet client", making connection to an adinnet
- server on a host, and send speech data to the server. The host-
- name should be specified by option "-server". The default port
- number is 5530, which can be altered by option "-port". The
- available adinnet server so far is adintool and Julius.
+ adintool is a upper version of adinrec with various functions.
+ Supported input device are: microphone input, a speech file, standard
+ tty input, and network socket (called adin-net server mode). Julius
+ plugin can be also used. Detected speech segments will be saved to
+ output devices: speech files, standard tty output, and network socket
+ (called adin-net client mode). For example, you can split the incoming
+ speech to segments and send them to Julius to be recognized.
- -out stdout
- Output to standard tty output in RAW, 16bit signed (big endian).
+ Output format is WAV, 16bit (signed short), monoral. If the file
+ already exist, it will be overridden.
OPTIONS
- -server host[,host...]
- Server(s) to connect with "-out adinnet". With multiple server,
- port number for each host should be specified by comma-separated
- list. (default: 5530)
-
- -port num[,host...]
- Port number to connect with "-out adinnet". Should be corre-
- spond with "-server"
-
- -nosegment
- Re-direct whole input speech data to output device, without
- speech detection and segmentation. With this option, the output
- filename does not have its four-digit ID appended.
-
- -oneshot
- Record only the first speech segment.
-
- -freq threshold
- Sampling frequency (Hz, default=16000)
-
- -48 Record in 48kHz, and down sampling to 16kHz.
-
- -lv threslevel
- Level threshold (0-32767, default=2000)
-
- -zc zerocrossnum
- Zero cross number threshold in a second (default=60)
-
- -headmargin msec
- Header margin of each speech segment (unit: milliseconds)
- (default: 400)
-
- -tailmargin msec
- Tail margin of each speech segment (unit: milliseconds)
- (default: 400)
-
- -nostrip
- Disable skipping of invalid zero samples (default: enabled)
-
- -zmean Enable zero mean subtraction to remove DC offset.
-
- -raw Output in RAW (no header) 16bit, big engian format (default:
- WAV)
-
- -autopause
- Automatically pause at each input end.
-
- -loosesync
- When connecting to multiple servers, avoid strict synchroniza-
- tion for server-side pause and resume command.
-
- -rewind msec
- By default, adintool will ignore speech input while being paused
- by server-side command. This may be a problem if an input
- begins while paused and then adintool resumes before the input
- ends. This option will send the last msec inputs before resum-
- ing.
-
-EXAMPLE
- Record microphone input only for the speech-detected part in
- "data.0000.wav", "data.0001.wav", ...:
-
- % adintool -in mic -out file -filename data
-
- Split a large speech data "foobar.raw" to "foobar.1500.wav", "foo-
- bar.1501.wav", etc:
-
- % adintool -in file -out file -filename foobar
- -startid 1500
- (enter the input filename after startup)
- enter filename->foobar.raw
- ....
-
- Send whole speech file to other host via tcp/ip socket:
-
- [sender]
- % adintool -in adinnet -out file -nosegment
- [receiver]
- % adintool -in file -out adinnet -server hostname
- -nosegment
-
- Send microphone input to Julius running on other host:
-
- (1) Transmit whole input, and let Julius execute
- speech detection and recognition:
-
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
- [adintool]
- % adintool -in mic -out adinnet -server hostname
- -nosegment
-
- (2) Detect speech segment at input client side
- (adintool), and transmit only the detected parts
- to Julius, and recognize them:
-
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
- [adintool]
- % adintool -in mic -out adinnet -server hostname
+ All Julius options can be set. Only audio input related options are
+ treated and others are silently skipped. Below is a list of options.
+ adintool specific options
+ -freq Hz
+ Set sampling rate in Hz. (default: 16,000)
+
+ -in inputdev
+ Audio input device. "mic" to capture via microphone input, "file"
+ for audio file input, and "stdin" to read raw data from
+ standard-input. For file input, file name prompt will appear after
+ startup. Use "adinnet" to make adintool as "adinnet server",
+ receiving data from client via network socket. Default port number
+ is 5530, which can be altered by option "-inport".
+
+ Alternatively, input device can be set by "-input" option, in which
+ case you can use plugin input.
+
+ -out outputdev
+ Audio output device store the data. Specify "file" to save to file,
+ in which the output filename should be given by "-filename". Use
+ "stdout" to standard out. "adinnet" will make adintool to be an
+ adinnet client, sending speech data to a server via tcp/ip socket.
+ When using "adinnet" output, the server name to send data should be
+ specified by "-server". The default port number is 5530, which can
+ be changed by "-port" option.
+
+ -inport num
+ When adintool becomes adinnet server to receive data (-in adinnet),
+ set the port number to listen. (default: 5530)
+
+ -server [host] [,host...]
+ When output to adinnet server (-out adinnet), set the hostname. You
+ can send to multiple hosts by specifying their hostnames as
+ comma-delimited list like "host1,host2,host3".
+
+ -port [num] [,num...]
+ When adintool send a data to adinnet server (-out adinnet), set the
+ port number to connect. (default: 5530) For multiple servers,
+ specify port numbers for all servers like "5530,5530,5531".
+
+ -filename file
+ When output to file (-out file), set the output filename. The actual
+ file name will be as "file.0000.wav" , "file.0001.wav" and so on,
+ where the four digit number increases as speech segment detected.
+ The initial number will be set to 0 by default, which can be changed
+ by "-startid" option. When using "-oneshot" option to save only the
+ first segment, the input will be saved as "file".
+
+ -startid number
+ At file output, set the initial file number. (default: 0)
+
+ -oneshot
+ Exit after the end of first speech segment.
+
+ -nosegment
+ Do not perform speech detection for input, just treat all the input
+ as a single valid segment.
+
+ -raw
+ Output as RAW file (no header).
+
+ -autopause
+ When output to adinnet server, adintool enter pause state at every
+ end of speech segment. It will restart when the destination adinnet
+ server sends it a resume signal.
+
+ -loosesync
+ When output to multiple adinnet server, not to do strict
+ synchronization for restart. By default, when adintool has entered
+ pause state, it will not restart until resume commands are received
+ from all servers. This option will allow restart at least one
+ restart command has arrived.
+
+ -rewind msec
+ When input is a live microphone device, and there has been some
+ continuing input at the moment adintool resumes, it start recording
+ backtracking by the specified milliseconds.
+
+ Concerning Julius options
+ -input {mic|rawfile|adinnet|stdin|netaudio|esd|alsa|oss}
+ Choose speech input source. Specify 'file' or 'rawfile' for waveform
+ file. On file input, users will be prompted to enter the file name
+ from stdin.
+
+ 'mic' is to get audio input from a default live microphone device,
+ and 'adinnet' means receiving waveform data via tcpip network from
+ an adinnet client. 'netaudio' is from DatLink/NetAudio input, and
+ 'stdin' means data input from standard input.
+
+ At Linux, you can choose API at run time by specifying alsa, oss and
+ esd.
+
+ -lv thres
+ Level threshold for speech input detection. Values should be in
+ range from 0 to 32767. (default: 2000)
+
+ -zc thres
+ Zero crossing threshold per second. Only input that goes over the
+ level threshold (-lv) will be counted. (default: 60)
+
+ -headmargin msec
+ Silence margin at the start of speech segment in milliseconds.
+ (default: 300)
+
+ -tailmargin msec
+ Silence margin at the end of speech segment in milliseconds.
+ (default: 400)
+
+ -zmean
+ This option enables DC offset removal.
+
+ -smpFreq Hz
+ Set sampling rate in Hz. (default: 16,000)
+
+ -48
+ Record input with 48kHz sampling, and down-sample it to 16kHz
+ on-the-fly. This option is valid for 16kHz model only. The
+ down-sampling routine was ported from sptk. (Rev. 4.0)
+
+ -NA devicename
+ Host name for DatLink server input (-input netaudio).
+
+ -adport port_number
+ With -input adinnet, specify adinnet port number to listen.
+ (default: 5530)
+
+ -nostrip
+ Julius by default removes successive zero samples in input speech
+ data. This option stop it.
+
+ -C jconffile
+ Load a jconf file at here. The content of the jconffile will be
+ expanded at this point.
+
+ -plugindir dirlist
+ Specify which directories to load plugin. If several direcotries
+ exist, specify them by colon-separated list.
+
+ENVIRONMENT VARIABLES
+ ALSADEV
+ (using mic input with alsa device) specify a capture device name. If
+ not specified, "default" will be used.
+
+ AUDIODEV
+ (using mic input with oss device) specify a capture device path. If
+ not specified, "/dev/dsp" will be used.
+
+ LATENCY_MSEC
+ Try to set input latency of microphone input in milliseconds.
+ Smaller value will shorten latency but sometimes make process
+ unstable. Default value will depend on the running OS.
+
+EXAMPLES
+ Record microphone input to files: "data.0000.wav", "data.0001.wav" and
+ so on:
+ Split a long speech file "foobar.raw" into "foobar.1500.wav",
+ "foobar.1501.wav" ...:
+ Copy an entire audio file via network socket.
+ Detect speech segment, send to Julius via network and recognize it:
SEE ALSO
- julius(1), adinrec(1)
+ julius ( 1 ) ,
+ adinrec ( 1 )
COPYRIGHT
- Copyright (c) 1991-2007 Kawahara Lab., Kyoto University
- Copyright (c) 2001-2007 Shikano Lab., Nara Institute of Science and
+ Copyright (c) 1997-2000 Information-technology Promotion Agency, Japan
+
+ Copyright (c) 1991-2008 Kawahara Lab., Kyoto University
+
+ Copyright (c) 2000-2005 Shikano Lab., Nara Institute of Science and
Technology
- Copyright (c) 2005-2007 Julius project team, Nagoya Institute of Tech-
- nology
-AUTHORS
- LEE Akinobu (Nagoya Institute of Technology, Japan)
- contact: juliu****@lists*****
+ Copyright (c) 2005-2008 Julius project team, Nagoya Institute of
+ Technology
LICENSE
- Same as Julius.
+ The same as Julius.
-4.3 Berkeley Distribution LOCAL ADINTOOL(1)
+ 10/02/2008 ADINTOOL(1)
Index: julius4/adintool/adintool.man
diff -u julius4/adintool/adintool.man:1.2 julius4/adintool/adintool.man:removed
--- julius4/adintool/adintool.man:1.2 Tue Dec 18 23:08:21 2007
+++ julius4/adintool/adintool.man Thu Oct 2 17:23:45 2008
@@ -1,193 +0,0 @@
-.de Sp
-.if t .sp .5v
-.if n .sp
-..
-.de Ip
-.br
-.ie \\n.$>=3 .ne \\$3
-.el .ne 3
-.IP "\\$1" \\$2
-..
-.TH ADINTOOL 1 LOCAL
-.UC 6
-.SH NAME
-adintool - audio tool to record/split/send/receive speech data for Julius
-.SH SYNOPSIS
-.B adintool -in inputdev -out outputdev [options...]
-.SH DESCRIPTION
-.I adintool
-analyzes speech input, finds speech segments skipping silence, and
-records the detected segments in various ways. It performs speech
-detection based on zerocross number and power (level), and records the
-detected parts to files or other output devices sucessively.
-.PP
-.I adintool
-is a highly-functioned version of
-.I adinrec.
-The supported input device are: microphone input, a speech file,
-standard tty input, and network socket (called adin-net server mode).
-The speech segments are saved to output devices: speech files,
-standard tty output, and network socket (called adin-net client mode).
-For example, you can record the incoming speech segments to files with
-successively-numbered suffixes, or send them to speech recognition
-engine
-.I julius
-to recognize them.
-.PP
-The output is not buffered: the receiver can get speech data with only
-a slight delay after a speech starts. The speech detection algorithm
-is as same as that of
-.I adinrec.
-.PP
-Output format is WAV, 16bit (signed short), monoral.
-If the file already exist, it will be overridden.
-.SH INPUT
-The input device should be specified by one of the following options:
-.Ip "\-in mic"
-Microphone input (default)
-.Ip "\-in file"
-Speech data file. Supported format is RAW (16bit big endian) and WAV
-(no compression) etc (depending on the compilation time setting).
-.br
-The input file name should be given later: prompt will appear after startup.
-.Ip "\-in adinnet"
-Make
-.I adintool
-"adinnet server", waiting for connection from adinnet client and
-receiving speech data from there via tcp/ip socket.
-.br
-Default port number is 5530, which can be altered by option "-port".
-.Ip "\-in netaudio"
-If supported, get input data from NetAudio/Datlink server. Host and
-unit name should be given with "-NA host:unit" option.
-.Ip "\-in stdin"
-Read speech data from standard tty input. Only RAW and WAV format is
-supported.
-.SH OUTPUT
-Specify one of these below to select an output device which the detected
-speech segments are going to written to.
-.Ip "\-out file"
-Output to files. The base filename should be given by option like
-"-filename foobar". Actually, the detected segments are recorded in
-separate files such as "foobar.0000", "foobar.0001" and so on. The
-four-digit ID begin with 0. This initial value can be set explicitly
-by option "-startid". The output format is WAV, 16bit signed. This
-can be changed by "-raw" option.
-.Ip "\-out adinnet"
-Make
-.I adintool
-"adinnet client", making connection to an adinnet server on a host,
-and send speech data to the server. The hostname should be specified
-by option "-server". The default port number is 5530, which can be
-altered by option "-port".
-The available adinnet server so far is
-.I adintool
-and
-.I Julius.
-.Ip "\-out stdout"
-Output to standard tty output in RAW, 16bit signed (big endian).
-.SH OPTIONS
-.Ip "\-server host[,host...]"
-Server(s) to connect with "-out adinnet". With multiple server, port
-number for each host should be specified by comma-separated
-list. (default: 5530)
-.Ip "\-port num[,host...]"
-Port number to connect with "-out adinnet". Should be correspond with "-server"
-.Ip "\-nosegment"
-Re-direct whole input speech data to output device, without speech
-detection and segmentation. With this option, the output filename
-does not have its four-digit ID appended.
-.Ip "\-oneshot"
-Record only the first speech segment.
-.Ip "\-freq threshold"
-Sampling frequency (Hz, default=16000)
-.Ip "\-48"
-Record in 48kHz, and down sampling to 16kHz.
-.Ip "\-lv threslevel"
-Level threshold (0-32767, default=2000)
-.Ip "\-zc zerocrossnum"
-Zero cross number threshold in a second (default=60)
-.Ip "\-headmargin msec"
-Header margin of each speech segment (unit: milliseconds)
-(default: 400)
-.Ip "\-tailmargin msec"
-Tail margin of each speech segment (unit: milliseconds)
-(default: 400)
-.Ip "\-nostrip"
-Disable skipping of invalid zero samples (default: enabled)
-.Ip "\-zmean"
-Enable zero mean subtraction to remove DC offset.
-.Ip "\-raw"
-Output in RAW (no header) 16bit, big engian format (default: WAV)
-.Ip "\-autopause"
-Automatically pause at each input end.
-.Ip "\-loosesync"
-When connecting to multiple servers, avoid strict synchronization
-for server-side pause and resume command.
-.Ip "\-rewind msec"
-By default, adintool will ignore speech input while being paused by
-server-side command. This may be a problem if an input begins while
-paused and then adintool resumes before the input ends. This option
-will send the last msec inputs before resuming.
-.SH "EXAMPLE"
-Record microphone input only for the speech-detected part in
-"data.0000.wav", "data.0001.wav", ...:
-.PP
- % adintool -in mic -out file -filename data
-.PP
-Split a large speech data "foobar.raw" to "foobar.1500.wav", "foobar.1501.wav", etc:
-.PP
- % adintool -in file -out file -filename foobar
- -startid 1500
- (enter the input filename after startup)
- enter filename->foobar.raw
- ....
-.PP
-Send whole speech file to other host via tcp/ip socket:
-.PP
- [sender]
- % adintool -in adinnet -out file -nosegment
-.BR
- [receiver]
- % adintool -in file -out adinnet -server hostname
- -nosegment
-.PP
-Send microphone input to
-.I Julius
-running on other host:
-.PP
-(1) Transmit whole input, and let Julius execute
- speech detection and recognition:
-.PP
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
-.BR
- [adintool]
- % adintool -in mic -out adinnet -server hostname
- -nosegment
-.PP
-(2) Detect speech segment at input client side
- (adintool), and transmit only the detected parts
- to Julius, and recognize them:
-.PP
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
-.BR
- [adintool]
- % adintool -in mic -out adinnet -server hostname
-
-.SH "SEE ALSO"
-julius(1), adinrec(1)
-.SH COPYRIGHT
-Copyright (c) 1991-2007 Kawahara Lab., Kyoto University
-.br
-Copyright (c) 2001-2007 Shikano Lab., Nara Institute of Science and Technology
-.br
-Copyright (c) 2005-2007 Julius project team, Nagoya Institute of Technology
-.SH AUTHORS
-LEE Akinobu (Nagoya Institute of Technology, Japan)
-.br
-contact: juliu****@lists*****
-.SH LICENSE
-Same as
-.I Julius.
Index: julius4/adintool/adintool.man.ja
diff -u julius4/adintool/adintool.man.ja:1.2 julius4/adintool/adintool.man.ja:removed
--- julius4/adintool/adintool.man.ja:1.2 Tue Dec 18 23:08:21 2007
+++ julius4/adintool/adintool.man.ja Thu Oct 2 17:23:45 2008
@@ -1,193 +0,0 @@
-.de Sp
-.if t .sp .5v
-.if n .sp
-..
-.de Ip
-.br
-.ie \\n.$>=3 .ne \\$3
-.el .ne 3
-.IP "\\$1" \\$2
-..
-.TH ADINTOOL 1 LOCAL
-.UC 6
-.SH NAME
-adintool - audio tool to record/split/send/receive speech data for Julius
-.SH SYNOPSIS
-.B adintool -in inputdev -out outputdev [options...]
-.SH DESCRIPTION
-.I adintool
-は，音声波形データ中の音声区間の検出および記録を連続的に行うツールです．
-入力音声に対して零交差数と振幅レベルに基づく音声区間検出を逐次行い，
-音声区間部分を連続出力します．
-.PP
-.I adintool
-は
-.I adinrec
-の高機能版です．音声データの入力元として，マイク入力・音声波形ファイル・
-標準入力・ネットワーク入力(adinnet サーバーモード)が選択できます．また，
-出力先として，音声波形ファイル・標準出力・ネットワーク出力(adinnet ク
-ライアントモード)が選択できます．特にネットワーク出力（adinnet クライ
-アントモード）では，
-.I julius
-へネットワーク経由で音声を送信して音声認識させることができます．
-.PP
-入力音声は音声区間ごとに自動分割され，逐次出力されます．
-音声区間の切り出しには
-.I adinrec
-と同じ，一定時間内の零交差数とパワー（振幅レベル）のしきい値を用います．
-音声区間開始と同時に音声出力が開始されます．出力としてファイル出力を選
-んだ場合は，連番ファイル名で検出された区間ごとに保存します．
-.PP
-サンプリング周波数は任意に設定可能です．形式は 16bit monoral です．書き出されるデータ形式は WAV, 16bit, モノラルです．
-既に同じ名前のファイルが存在する場合は上書きします．
-.SH INPUT
-音声を読み込む入力デバイスは以下のうちどれかを指定します．
-.Ip "\-in mic"
-マイク入力（デフォルト）．
-.Ip "\-in file"
-音声波形ファイル．形式は RAW (16bit big endian)，WAV(無圧縮)など
-（コンパイル時の設定による）．
-.br
-なお，入力ファイル名は起動後に，プロンプトに対して入力する．
-.Ip "\-in adinnet"
-adinnet サーバーとなってネットワーク経由で adinnet クライアントから音声データを受け取る．
-adinnet クライアントからのTCP/IP接続を待ち，
-接続が確立した後は adinnet クライアントから音声データを受け取る．
-.br
-ポート番号のデフォルトは 5530 である．これはオプション "-port" で変更可能．
-.Ip "\-in netaudio"
-(サポートされていれば）音声データをNetaudio/DatLinkサーバーから受け取
-る．サーバのホスト名とユニット名を "-NA host:unit" で指定する必要があ
-る．
-.Ip "\-in stdin"
-標準入力．音声データ形式は RAW, WAV のみ．
-.SH OUTPUT
-検出した音声区間の音声データを書き出す出力デバイスとして，以下のうちど
-れかを指定します．
-.Ip "\-out file"
-ファイルへ出力する．出力ファイル名は別のオプション"-filename foobar"
-の形で与える．実際には "foobar.0000" , "foobar.0001" ... のように区間ごとに，指
-定した名前の末尾に4桁のIDをつけた名前で記録されなる． ID は 0
-を初期値として，音声区間検出ごとに１増加する．初期値はオプション
-"-startid" で変更可能である．また，出力ファイル形式は 16bit WAV 形式である．
-RAW 形式で出力するには "-raw" オプションを指定する．
-.Ip "\-out adinnet"
-adinnet クライアントとなって，ネットワーク経由で adinnet サーバへ音声
-データを送る．入力の時とは逆に，
-.I adintool
-は adinnet クライアントとなり，adinnet サーバーへ接続後，音声データを
-送信する．adinnet サーバーとしては，
-.I adintool
-および
-.I Julius
-のadinnet入力が挙げられる．
-.br
-"-server" で送信先のadinnetサーバのホスト名を指定する．また
-ポート番号のデフォルトは 5530 である．これはオプション "-port" で変更可能．
-.Ip "\-out stdout"
-標準出力へ出力する．形式は RAW, 16bit signed (big endian) である．
-.PP
-.SH OPTIONS
-.Ip "\-server host[,host...]"
-"-out adinnet" で送信するサーバのホスト名を指定する．コンマ区切りで
-複数のサーバを指定可能．
-.Ip "\-port num[,host...]"
-"-out adinnet" で送信するサーバのポート番号．複数サーバ使用時は
-コンマ区切りで "-server"に対応させて全ての番号を指定すること． (default: 5530)
-.Ip "\-nosegment"
-入力音声に対して音声区間の検出を行わず，そのまま出力へリダイレクトする．
-ファイル出力の場合，ファイル名の末尾に4桁のIDは付与されなくなる．
-.Ip "\-oneshot"
-入力開始後，一番最初の１音声区間のみを送信後，終了する．
-.Ip "\-freq threshold"
-サンプリング周波数．単位は Hz (default: 16000)
-.Ip "\-48"
-48kHzサンプリング後，16kHzにダウンサンプリングする．
-.Ip "\-lv threslevel"
-波形の振幅レベルのしきい値 (0 - 32767)．(default: 2000)．
-.Ip "\-zc zerocrossnum"
-１秒あたりの零交差数のしきい値 (default: 60)
-.Ip "\-headmargin msec"
-音声区間開始部の直前のマージン．単位はミリ秒
-(default: 400)
-.Ip "\-tailmargin msec"
-音声区間終了部の直後のマージン．単位はミリ秒
-(default: 400)
-.Ip "\-nostrip"
-無効な 0 サンプルの自動除去を行わないようにする．
-デフォルトは自動除去を行う．
-.Ip "\-zmean"
-DC成分除去を行う．
-.Ip "\-raw"
-ファイル出力形式を RAW, 16bit signed (big endian) にする．
-デフォルトは WAV 形式である．
-.Ip "\-autopause"
-入力終了ごとに自動的に pause 状態に入る．
-.Ip "\-loosesync"
-複数サーバ接続時，複数サーバからの pause や resume コマンドに対して
-厳密な同期を行わないようにする．
-.Ip "\-rewind msec"
-通常，adintool は pause 中の入力を無視する．このため，pause中に入力が開始
-され，その入力が終了する前にサーバコマンドにより resume したときに
-極端に短い音声フラグメントが検出されることとなる．このオプションを
-指定することで，resume時に音声入力中の場合，入力を resume 時点から
-指定した長さだけ遡って送信する．
-.SH "EXAMPLE"
-マイクからの音声入力を，発話ごとに "data.0000.wav" から順に記録する：
-.PP
- % adintool -in mic -out file -filename data
-.PP
-巨大な収録音声ファイル "foobar.raw"を音声区間ごとに
-"foobar.1500.wav" "foobar.1501.wav" ... に分割する：
-.PP
- % adintool -in file -out file -filename foobar
- -startid 1500
- (起動後プロンプトに対してファイル名を入力)
- enter filename->foobar.raw
-.PP
-ネットワーク経由で音声ファイルを転送する(区間検出なし)：
-.PP
- [受信側]
- % adintool -in adinnet -out file -nosegment
-.BR
- [送信側]
- % adintool -in file -out adinnet -server hostname
- -nosegment
-.PP
-マイクからの入力音声を別サーバーの
-.I Julius
-に送る：
-.PP
-(1) 入力データを全て送信し，Julius側で区間検出・認識：
-.PP
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
-.BR
- [adintool]
- % adintool -in mic -out adinnet -server hostname
- -nosegment
-.PP
-(2) 入力データはクライアント(adintool)側で区間検出し，検出した区間だけ
-を順に Julius へ送信・認識：
-.PP
- [Julius]
- % julius -C xxx.jconf ... -input adinnet
-.BR
- [adintool]
- % adintool -in mic -out adinnet -server hostname
-.SH "SEE ALSO"
-julius(1), adinrec(1)
-.SH BUGS
-バグ報告・問い合わせ・コメントなどは
-juli****@lists***** までお願いします．
-.SH COPYRIGHT
-Copyright (c) 1991-2006 京都大学 河原研究室
-.br
-Copyright (c) 2000-2005 奈良先端科学技術大学院大学 鹿野研究室
-.br
-Copyright (c) 2005-2006 名古屋工業大学 Julius開発チーム
-.SH AUTHORS
-李 晃伸 (名古屋工業大学) が実装しました．
-.SH LICENSE
-.I Julius
-の使用許諾に準じます．