Knowledge

Festival Speech Synthesis System

Source 📝

571: 25: 589: 587: 367:
The Festvox project aims to make the building of new synthetic voices more systematic and better documented, making it possible for anyone to build a new voice. It is distributed under a
588: 42: 89: 386:
for building synthetic voices for Festival. It includes a step-by-step tutorial with examples in document called "Building Synthetic Voices".
61: 68: 1226: 929: 681: 580: 75: 1216: 650: 1231: 595:
A recording of an earlier version of this article made with the text2audio script, which uses Festival Speech Synthesis System.
57: 999: 1221: 108: 1076: 192: 638: 994: 838: 621: 674: 46: 82: 293: 288:, as well as an environment for development and research of speech synthesis techniques. It is written in 732: 427: 144: 989: 395: 266: 1004: 667: 974: 818: 1165: 1050: 919: 904: 262: 133: 35: 1160: 1114: 1129: 868: 751: 368: 270: 1124: 833: 791: 261:, Paul Taylor and Richard Caley at the Centre for Speech Technology Research (CSTR) at the 8: 415: 407: 297: 1144: 1134: 1045: 197: 647: 1109: 448: 324: 984: 934: 690: 352: 344: 340: 332: 320: 312: 304: 254: 204: 180: 828: 654: 642: 625: 356: 348: 308: 1175: 328: 316: 303:
Festival is designed to support multiple languages, and comes with support for
281: 185: 613: 469: 226: 1210: 1195: 1185: 1104: 848: 698: 379: 258: 214: 1190: 1139: 979: 808: 1119: 1035: 843: 722: 383: 372: 274: 210: 954: 1060: 1025: 924: 914: 853: 635: 604: 127: 618: 1055: 899: 878: 873: 727: 411: 24: 1086: 1030: 949: 944: 863: 823: 717: 659: 517: 813: 746: 541: 1170: 1040: 767: 713: 394:
Flite is a small run-time speech synthesis engine developed at
1180: 1081: 1009: 909: 883: 858: 777: 336: 289: 173: 323:. Voice packages exist for several other languages, such as 939: 630: 493: 449:"The Architecture of the Festival Speech Synthesis System" 285: 265:. Substantial contributions have also been provided by 132:
Centre for Speech Technology Research (CSTR) of the
49:. Unsourced material may be challenged and removed. 1208: 675: 269:and other sites. It is distributed under a 682: 668: 398:, derived from both Festival and Festvox. 300:for general customization and extension. 109:Learn how and when to remove this message 414:. Festival is pre-packaged for several 1209: 401: 663: 689: 614:The Festival Speech Synthesis System 47:adding citations to reliable sources 18: 13: 1000:Texas Instruments LPC Speech Chips 569: 446: 58:"Festival Speech Synthesis System" 14: 1243: 562: 1077:Speech Synthesis Markup Language 738:Festival Speech Synthesis System 603:Problems playing this file? See 585: 581:Festival_Speech_Synthesis_System 251:Festival Speech Synthesis System 23: 1227:Free software programmed in C++ 839:Microsoft text-to-speech voices 542:"CMU Flite: Speech Synthesizer" 378:Festvox is a suite of tools by 257:system originally developed by 34:needs additional citations for 1217:Free speech synthesis software 534: 510: 486: 462: 440: 1: 1232:Singing software synthesizers 433: 7: 518:"Building Synthetic Voices" 428:Orca (assistive technology) 421: 253:is a general multi-lingual 150:2.5 / December 2017 10: 1248: 741: 456:Carnegie Mellon University 396:Carnegie Mellon University 362: 267:Carnegie Mellon University 152:; 6 years ago 1153: 1095: 1069: 1018: 1005:General Instrument SP0256 967: 892: 801: 790: 760: 706: 697: 648:Lyricos singing synthesis 636:Flinger singing synthesis 221: 203: 191: 179: 169: 165: 143: 139: 126: 1222:Free multimedia software 819:Software Automatic Mouth 389: 1166:Concatenative synthesis 1051:Microsoft Speech Server 920:NIAONiao Virtual Singer 263:University of Edinburgh 134:University of Edinburgh 1161:Articulatory synthesis 1115:Franklin Seaney Cooper 574: 1130:Wolfgang von Kempelen 910:CeVIO Creative Studio 869:CeVIO Creative Studio 752:Automatik Text Reader 573: 369:free software license 271:free software license 1125:Haskins Laboratories 834:Microsoft Speech API 406:There is a Festival 284:system with various 43:improve this article 416:Linux distributions 402:Linux compatibility 298:command interpreter 123: 1135:Ignatius Mattingly 653:2017-04-26 at the 641:2012-03-30 at the 624:2009-01-24 at the 575: 198:Speech synthesizer 121: 1204: 1203: 1110:Catherine Browman 963: 962: 786: 785: 773:Lyricos / Flinger 590: 474:www.cstr.ed.ac.uk 325:Castilian Spanish 280:It offers a full 247: 246: 119: 118: 111: 93: 1239: 1046:Windows Narrator 985:Pattern playback 935:Symphonic Choirs 799: 798: 704: 703: 691:Speech synthesis 684: 677: 670: 661: 660: 592: 591: 572: 556: 555: 553: 552: 538: 532: 531: 529: 528: 514: 508: 507: 505: 504: 490: 484: 483: 481: 480: 466: 460: 459: 453: 444: 315:pronunciation), 255:speech synthesis 243: 240: 238: 236: 234: 232: 230: 228: 181:Operating system 160: 158: 153: 124: 120: 114: 107: 103: 100: 94: 92: 51: 27: 19: 1247: 1246: 1242: 1241: 1240: 1238: 1237: 1236: 1207: 1206: 1205: 1200: 1149: 1097: 1091: 1065: 1014: 959: 888: 829:Microsoft Agent 793: 782: 756: 693: 688: 655:Wayback Machine 643:Wayback Machine 626:Wayback Machine 610: 609: 601: 599: 598: 597: 596: 593: 586: 583: 576: 570: 565: 560: 559: 550: 548: 546:www.festvox.org 540: 539: 535: 526: 524: 522:www.festvox.org 516: 515: 511: 502: 500: 498:www.festvox.org 494:"Festvox: Home" 492: 491: 487: 478: 476: 468: 467: 463: 451: 445: 441: 436: 424: 404: 392: 371:similar to the 365: 273:similar to the 225: 161: 156: 154: 151: 115: 104: 98: 95: 52: 50: 40: 28: 17: 12: 11: 5: 1245: 1235: 1234: 1229: 1224: 1219: 1202: 1201: 1199: 1198: 1193: 1188: 1183: 1178: 1176:Inverse filter 1173: 1168: 1163: 1157: 1155: 1151: 1150: 1148: 1147: 1142: 1137: 1132: 1127: 1122: 1117: 1112: 1107: 1101: 1099: 1093: 1092: 1090: 1089: 1084: 1079: 1073: 1071: 1067: 1066: 1064: 1063: 1058: 1053: 1048: 1043: 1038: 1033: 1028: 1022: 1020: 1016: 1015: 1013: 1012: 1007: 1002: 997: 992: 987: 982: 977: 971: 969: 965: 964: 961: 960: 958: 957: 952: 947: 942: 937: 932: 927: 922: 917: 912: 907: 902: 896: 894: 890: 889: 887: 886: 881: 876: 871: 866: 861: 856: 851: 846: 841: 836: 831: 826: 821: 816: 811: 805: 803: 796: 788: 787: 784: 783: 781: 780: 775: 770: 764: 762: 758: 757: 755: 754: 749: 744: 735: 730: 725: 720: 710: 708: 701: 695: 694: 687: 686: 679: 672: 664: 658: 657: 645: 633: 628: 616: 600: 594: 584: 579: 578: 577: 568: 567: 566: 564: 563:External links 561: 558: 557: 533: 509: 485: 461: 447:Taylor, Paul. 438: 437: 435: 432: 431: 430: 423: 420: 403: 400: 391: 388: 364: 361: 282:text to speech 245: 244: 223: 219: 218: 207: 201: 200: 195: 189: 188: 186:Cross-platform 183: 177: 176: 171: 167: 166: 163: 162: 149: 147: 145:Stable release 141: 140: 137: 136: 130: 117: 116: 31: 29: 22: 15: 9: 6: 4: 3: 2: 1244: 1233: 1230: 1228: 1225: 1223: 1220: 1218: 1215: 1214: 1212: 1197: 1196:Voice cloning 1194: 1192: 1189: 1187: 1186:Phase vocoder 1184: 1182: 1179: 1177: 1174: 1172: 1169: 1167: 1164: 1162: 1159: 1158: 1156: 1152: 1146: 1143: 1141: 1138: 1136: 1133: 1131: 1128: 1126: 1123: 1121: 1118: 1116: 1113: 1111: 1108: 1106: 1105:Alan W. Black 1103: 1102: 1100: 1094: 1088: 1085: 1083: 1080: 1078: 1075: 1074: 1072: 1068: 1062: 1059: 1057: 1054: 1052: 1049: 1047: 1044: 1042: 1039: 1037: 1034: 1032: 1029: 1027: 1024: 1023: 1021: 1017: 1011: 1008: 1006: 1003: 1001: 998: 996: 993: 991: 988: 986: 983: 981: 978: 976: 973: 972: 970: 966: 956: 953: 951: 948: 946: 943: 941: 938: 936: 933: 931: 928: 926: 923: 921: 918: 916: 913: 911: 908: 906: 903: 901: 898: 897: 895: 891: 885: 882: 880: 877: 875: 872: 870: 867: 865: 862: 860: 857: 855: 852: 850: 849:Voice browser 847: 845: 842: 840: 837: 835: 832: 830: 827: 825: 822: 820: 817: 815: 812: 810: 807: 806: 804: 800: 797: 795: 789: 779: 776: 774: 771: 769: 766: 765: 763: 759: 753: 750: 748: 745: 743: 739: 736: 734: 731: 729: 726: 724: 721: 719: 715: 712: 711: 709: 705: 702: 700: 699:Free software 696: 692: 685: 680: 678: 673: 671: 666: 665: 662: 656: 652: 649: 646: 644: 640: 637: 634: 632: 629: 627: 623: 620: 617: 615: 612: 611: 608: 606: 582: 547: 543: 537: 523: 519: 513: 499: 495: 489: 475: 471: 465: 457: 450: 443: 439: 429: 426: 425: 419: 417: 413: 409: 399: 397: 387: 385: 381: 380:Alan W. Black 376: 374: 370: 360: 358: 354: 350: 346: 342: 338: 334: 330: 326: 322: 318: 314: 310: 306: 301: 299: 295: 291: 287: 283: 278: 276: 272: 268: 264: 260: 259:Alan W. Black 256: 252: 242: 224: 220: 216: 215:Free software 212: 208: 206: 202: 199: 196: 194: 190: 187: 184: 182: 178: 175: 172: 168: 164: 148: 146: 142: 138: 135: 131: 129: 125: 113: 110: 102: 99:February 2013 91: 88: 84: 81: 77: 74: 70: 67: 63: 60: –  59: 55: 54:Find sources: 48: 44: 38: 37: 32:This article 30: 26: 21: 20: 16:Free software 1191:Self-voicing 1140:Philip Rubin 1019:Applications 980:Mockingboard 809:Amazon Polly 792:Proprietary 772: 737: 619:Flite at CMU 602: 549:. Retrieved 545: 536: 525:. Retrieved 521: 512: 501:. Retrieved 497: 488: 477:. Retrieved 473: 464: 455: 442: 405: 393: 377: 366: 302: 279: 250: 248: 128:Developer(s) 105: 96: 86: 79: 72: 65: 53: 41:Please help 36:verification 33: 1120:Gunnar Fant 1098:Researchers 1096:Developers/ 1036:Dr. Sbaitso 844:Readspeaker 723:Gnopernicus 384:Kevin Lenzo 373:MIT License 275:BSD License 211:MIT License 209:Similar to 1211:Categories 1061:Voice font 1026:AOLbyPhone 925:PPG Phonem 915:Chipspeech 854:CoolSpeech 605:media help 551:2019-03-25 527:2019-03-25 503:2019-03-25 479:2019-03-25 470:"Festival" 434:References 170:Written in 69:newspapers 1070:Protocols 1056:PlainTalk 900:Alter/Ego 879:LaLaVoice 874:Voiceroid 768:eCantorix 728:Gnuspeech 412:GStreamer 239:/festival 237:/projects 1087:VoiceXML 1031:DialogOS 950:Vocaloid 945:Vocalina 930:Realivox 864:CereProc 824:Talk It! 802:Speaking 794:software 718:eSpeakNG 707:Speaking 651:Archived 639:Archived 622:Archived 422:See also 313:American 122:Festival 1154:Process 975:Echo II 968:Machine 955:Xiaoice 893:Singing 814:DECtalk 761:Singing 747:FreeTTS 631:Festvox 408:plug-in 363:Festvox 353:Russian 345:Marathi 341:Italian 333:Finnish 321:Spanish 309:British 305:English 292:with a 222:Website 205:License 157:2017-12 155: ( 83:scholar 1171:Currah 1145:Yamaha 1041:MBROLA 990:Phasor 905:Cantor 714:eSpeak 357:Telugu 349:Polish 319:, and 296:-like 294:Scheme 85:  78:  71:  64:  56:  1181:PSOLA 1082:SABLE 1010:TuVox 884:15.ai 859:IVONA 778:Sinsy 742:Flite 452:(PDF) 390:Flite 337:Hindi 329:Czech 317:Welsh 229:.cstr 90:JSTOR 76:books 995:RIAS 940:UTAU 733:Orca 410:for 382:and 355:and 311:and 286:APIs 249:The 193:Type 62:news 290:C++ 235:.uk 233:.ac 231:.ed 227:www 174:C++ 45:by 1213:: 544:. 520:. 496:. 472:. 454:. 418:. 375:. 359:. 351:, 347:, 343:, 339:, 335:, 331:, 327:, 277:. 740:/ 716:/ 683:e 676:t 669:v 607:. 554:. 530:. 506:. 482:. 458:. 307:( 241:/ 217:) 213:( 159:) 112:) 106:( 101:) 97:( 87:· 80:· 73:· 66:· 39:.

Index


verification
improve this article
adding citations to reliable sources
"Festival Speech Synthesis System"
news
newspapers
books
scholar
JSTOR
Learn how and when to remove this message
Developer(s)
University of Edinburgh
Stable release
C++
Operating system
Cross-platform
Type
Speech synthesizer
License
MIT License
Free software
www.cstr.ed.ac.uk/projects/festival/
speech synthesis
Alan W. Black
University of Edinburgh
Carnegie Mellon University
free software license
BSD License
text to speech

Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.