Global Patent Index - EP 3327723 A1

EP 3327723 A1 20180530 - METHOD FOR SLOWING DOWN A SPEECH IN AN INPUT MEDIA CONTENT

Title (en)

METHOD FOR SLOWING DOWN A SPEECH IN AN INPUT MEDIA CONTENT

Title (de)

VERFAHREN ZUM VERLANGSAMEN VON SPRACHE IN EINEM EINGANGSMEDIENINHALT

Title (fr)

PROCÉDÉ POUR FREINER UN DISCOURS DANS UN CONTENU MULTIMÉDIA ENTRÉ

Publication

EP 3327723 A1 20180530 (EN)

Application

EP 16306550 A 20161124

Priority

EP 16306550 A 20161124

Abstract (en)

The present invention relates to a method for slowing down speech in an input audio signal constituted by a sequence of audio frames, comprising performing steps of: (a) classifying the audio frames as speech, non-speech, or pause, so as to divide said audio signal into speech segments bounded by non-speech segments; (b) for each speech segment: 1. dividing it into a sequence of intervowel segments; 2. calculating an average intervowel distance ( T avg ), and determining a non-linear stretching transfer function mapping an input intervowel distance ( T in ) to an output intervowel distance ( T out ) as a function of said average intervowel distance ( T avg ) and a given target intervowel distance ( T target ); 3. for each intervowel segment, stretching it using the determined stretching transfer function so as to generate updated audio frames; (c) generating as output signal the input audio signal wherein for each intervowel segment of each speech segment the corresponding audio frames have been replaced by the updated audio frames. The present invention also relates to an equipment for carrying out said method.

IPC 8 full level

G10L 21/04 (2013.01)

CPC (source: EP)

G10L 21/04 (2013.01); G10L 25/15 (2013.01)

Citation (applicant)

  • US 7853447 B2 20101214 - YEN MING HSIANG [TW], et al
  • US 6484137 B1 20021119 - TANIGUCHI HIROTSUGU [JP], et al
  • US 7412379 B2 20080812 - TAORI RAKESH [NL], et al
  • GHAHREMANI; PEGAH; BAGHER BABA ALI; DANIEL POVEY; KORBINIAN RIEDHAMMER; JAN TRMAL; SANJEEV KHUDANPUR: "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP", 2014, IEEE, article "A pitch extraction algorithm tuned for automatic speech recognition", pages: 2494 - 2498

Citation (search report)

Designated contracting state (EPC)

AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

Designated extension state (EPC)

BA ME

DOCDB simple family (publication)

EP 3327723 A1 20180530; WO 2018096541 A1 20180531

DOCDB simple family (application)

EP 16306550 A 20161124; IL 2017051286 W 20171126