17:
729:
65:
PSOLA works by dividing the speech waveform in small overlapping segments. To change the pitch of the signal, the segments are moved further apart (to decrease the pitch) or closer together (to increase the pitch). To change the duration of the signal, the segments are then repeated multiple times
107:
442:
194:
86:
127:
Charpentier, F.; Stella, M. (1986). "Diphone synthesis using an overlap-add technique for speech waveforms concatenation".
766:
254:
512:
66:(to increase the duration) or some are eliminated (to decrease the duration). The segments are then combined using the
16:
589:
285:
250:
507:
351:
187:
115:(Ph.D. thesis). Seria Jezykoznawstwo Stosowane. Vol. 17. Uniwersytet Im. Adama Mickiewicza W Poznaniu.
245:
502:
790:
785:
517:
180:
487:
331:
759:
678:
563:
432:
417:
673:
627:
642:
381:
264:
74:
637:
346:
304:
8:
166:
752:
657:
647:
558:
140:
622:
129:
ICASSP '86. IEEE International
Conference on Acoustics, Speech, and Signal Processing
47:
43:
144:
497:
447:
203:
132:
59:
51:
341:
136:
740:
736:
688:
779:
708:
698:
617:
361:
211:
109:
Analiza cech suprasegmentalnych jezyka polskiego na potrzeby technologii mowy
55:
728:
703:
652:
492:
321:
632:
548:
356:
235:
67:
467:
161:
573:
538:
437:
427:
366:
568:
412:
391:
386:
240:
20:
Oscillograms, spectrograms and intonograms of Polish expression (a)
599:
543:
462:
457:
376:
336:
230:
172:
326:
259:
683:
553:
280:
226:
594:
522:
422:
396:
371:
290:
452:
169:(PDF format; see page 35, which is page 44 of the PDF)
126:
62:of a speech signal. It was invented around 1986.
42:(Pitch Synchronous Overlap and Add) is a digital
777:
105:
162:Changing Pitch with PSOLA for Voice Conversion
760:
188:
167:A thesis that discusses PSOLA with diagrams
767:
753:
195:
181:
15:
87:Audio time stretching and pitch scaling
778:
735:This technology-related article is a
176:
723:
202:
131:. Vol. 11. pp. 2015–2018.
13:
513:Texas Instruments LPC Speech Chips
14:
802:
155:
727:
590:Speech Synthesis Markup Language
251:Festival Speech Synthesis System
73:PSOLA can be used to change the
352:Microsoft text-to-speech voices
54:. It can be used to modify the
120:
99:
1:
92:
739:. You can help Knowledge by
7:
137:10.1109/ICASSP.1986.1168657
80:
10:
807:
722:
666:
608:
582:
531:
518:General Instrument SP0256
480:
405:
314:
303:
273:
219:
210:
332:Software Automatic Mouth
106:Grazyna Demenko (1999).
679:Concatenative synthesis
564:Microsoft Speech Server
433:NIAONiao Virtual Singer
674:Articulatory synthesis
628:Franklin Seaney Cooper
50:and more specifically
36:
643:Wolfgang von Kempelen
423:CeVIO Creative Studio
382:CeVIO Creative Studio
265:Automatik Text Reader
19:
638:Haskins Laboratories
347:Microsoft Speech API
77:of a speech signal.
46:technique used for
648:Ignatius Mattingly
37:
748:
747:
717:
716:
623:Catherine Browman
476:
475:
299:
298:
286:Lyricos / Flinger
48:speech processing
44:signal processing
798:
791:Technology stubs
786:Speech synthesis
769:
762:
755:
731:
724:
559:Windows Narrator
498:Pattern playback
448:Symphonic Choirs
312:
311:
217:
216:
204:Speech synthesis
197:
190:
183:
174:
173:
149:
148:
124:
118:
116:
114:
103:
52:speech synthesis
806:
805:
801:
800:
799:
797:
796:
795:
776:
775:
774:
773:
720:
718:
713:
662:
610:
604:
578:
527:
472:
401:
342:Microsoft Agent
306:
295:
269:
206:
201:
158:
153:
152:
125:
121:
112:
104:
100:
95:
83:
12:
11:
5:
804:
794:
793:
788:
772:
771:
764:
757:
749:
746:
745:
732:
715:
714:
712:
711:
706:
701:
696:
691:
689:Inverse filter
686:
681:
676:
670:
668:
664:
663:
661:
660:
655:
650:
645:
640:
635:
630:
625:
620:
614:
612:
606:
605:
603:
602:
597:
592:
586:
584:
580:
579:
577:
576:
571:
566:
561:
556:
551:
546:
541:
535:
533:
529:
528:
526:
525:
520:
515:
510:
505:
500:
495:
490:
484:
482:
478:
477:
474:
473:
471:
470:
465:
460:
455:
450:
445:
440:
435:
430:
425:
420:
415:
409:
407:
403:
402:
400:
399:
394:
389:
384:
379:
374:
369:
364:
359:
354:
349:
344:
339:
334:
329:
324:
318:
316:
309:
301:
300:
297:
296:
294:
293:
288:
283:
277:
275:
271:
270:
268:
267:
262:
257:
248:
243:
238:
233:
223:
221:
214:
208:
207:
200:
199:
192:
185:
177:
171:
170:
164:
157:
156:External links
154:
151:
150:
119:
117:Fig.7.1, p.63.
97:
96:
94:
91:
90:
89:
82:
79:
9:
6:
4:
3:
2:
803:
792:
789:
787:
784:
783:
781:
770:
765:
763:
758:
756:
751:
750:
744:
742:
738:
733:
730:
726:
725:
721:
710:
709:Voice cloning
707:
705:
702:
700:
699:Phase vocoder
697:
695:
692:
690:
687:
685:
682:
680:
677:
675:
672:
671:
669:
665:
659:
656:
654:
651:
649:
646:
644:
641:
639:
636:
634:
631:
629:
626:
624:
621:
619:
618:Alan W. Black
616:
615:
613:
607:
601:
598:
596:
593:
591:
588:
587:
585:
581:
575:
572:
570:
567:
565:
562:
560:
557:
555:
552:
550:
547:
545:
542:
540:
537:
536:
534:
530:
524:
521:
519:
516:
514:
511:
509:
506:
504:
501:
499:
496:
494:
491:
489:
486:
485:
483:
479:
469:
466:
464:
461:
459:
456:
454:
451:
449:
446:
444:
441:
439:
436:
434:
431:
429:
426:
424:
421:
419:
416:
414:
411:
410:
408:
404:
398:
395:
393:
390:
388:
385:
383:
380:
378:
375:
373:
370:
368:
365:
363:
362:Voice browser
360:
358:
355:
353:
350:
348:
345:
343:
340:
338:
335:
333:
330:
328:
325:
323:
320:
319:
317:
313:
310:
308:
302:
292:
289:
287:
284:
282:
279:
278:
276:
272:
266:
263:
261:
258:
256:
252:
249:
247:
244:
242:
239:
237:
234:
232:
228:
225:
224:
222:
218:
215:
213:
212:Free software
209:
205:
198:
193:
191:
186:
184:
179:
178:
175:
168:
165:
163:
160:
159:
146:
142:
138:
134:
130:
123:
111:
110:
102:
98:
88:
85:
84:
78:
76:
71:
69:
63:
61:
57:
53:
49:
45:
41:
35:
31:
27:
23:
18:
741:expanding it
734:
719:
704:Self-voicing
693:
653:Philip Rubin
532:Applications
493:Mockingboard
322:Amazon Polly
305:Proprietary
128:
122:
108:
101:
72:
64:
39:
38:
33:
29:
25:
21:
633:Gunnar Fant
611:Researchers
609:Developers/
549:Dr. Sbaitso
357:Readspeaker
236:Gnopernicus
70:technique.
68:overlap add
780:Categories
574:Voice font
539:AOLbyPhone
438:PPG Phonem
428:Chipspeech
367:CoolSpeech
93:References
583:Protocols
569:PlainTalk
413:Alter/Ego
392:LaLaVoice
387:Voiceroid
281:eCantorix
241:Gnuspeech
600:VoiceXML
544:DialogOS
463:Vocaloid
458:Vocalina
443:Realivox
377:CereProc
337:Talk It!
315:Speaking
307:software
231:eSpeakNG
220:Speaking
145:62440369
81:See also
60:duration
34:"na wóz"
26:"ja jem"
667:Process
488:Echo II
481:Machine
468:Xiaoice
406:Singing
327:DECtalk
274:Singing
260:FreeTTS
75:prosody
30:"nawóz"
22:"jajem"
684:Currah
658:Yamaha
554:MBROLA
503:Phasor
418:Cantor
227:eSpeak
143:
694:PSOLA
595:SABLE
523:TuVox
397:15.ai
372:IVONA
291:Sinsy
255:Flite
141:S2CID
113:(PDF)
56:pitch
40:PSOLA
737:stub
508:RIAS
453:UTAU
246:Orca
58:and
32:(d)
28:(c)
24:(b)
133:doi
782::
139:.
768:e
761:t
754:v
743:.
253:/
229:/
196:e
189:t
182:v
147:.
135::
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.