Title:
MACHINE-SYNTHESIZED SPEECH RECOGNITION METHOD, APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/051566
Kind Code:
A1
Abstract:
Provided is a machine-synthesized speech recognition method, said method comprising: when speech to be recognized is received, collecting an acoustic waveform of a predetermined time period of the speech to be recognized (S110); segmenting separately according to a plurality of predetermined segmentation rules to obtain a plurality of sub-acoustic waveform groups (S120); obtaining the peak frequency of each sub-acoustic waveform among the plurality of sub-acoustic waveform groups (S130); from among all of the sub-acoustic waveforms, acquiring a plurality of sub-acoustic waveforms having a peak frequency greater than an associated frequency threshold to obtain a plurality of high-frequency sub-acoustic waveforms (S140); obtaining the peak frequencies of the plurality of high-frequency sub-acoustic waveforms, the quantity of the plurality of high-frequency sub-acoustic waveforms, and the average value of each high-frequency sub-acoustic wave (S150); determining whether the speech to be recognized is machine-synthesized speech (S160). In the method, key features are extracted, effectively improving the accuracy and efficiency of identification of machine-synthesized speech.
Inventors:
ZHAO MOYAN (CN)
WANG HONGWEI (CN)
WANG HONGWEI (CN)
Application Number:
PCT/CN2019/117681
Publication Date:
March 25, 2021
Filing Date:
November 12, 2019
Export Citation:
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G10L17/00; G10L15/22
Foreign References:
| CN105513598A | 2016-04-20 | |||
| CN109300479A | 2019-02-01 | |||
| CN109920447A | 2019-06-21 | |||
| US20090259468A1 | 2009-10-15 | |||
| US20180254046A1 | 2018-09-06 |
Other References:
SAHIDULLAH MD, KINNUNEN TOMI, HANILCI CEMAL: "A Comparison of Features for Synthetic Speech Detection", ISCA (THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION), 1 January 2015 (2015-01-01), XP055796299, Retrieved from the Internet [retrieved on 20210416]
JALALUDDIN AKBAR MUHAMMAD: "A Overview of Spoof Speech Detection for Automatic Speaker Verification", RESEARCHGATE, 28 February 2019 (2019-02-28), XP055796300
JALALUDDIN AKBAR MUHAMMAD: "A Overview of Spoof Speech Detection for Automatic Speaker Verification", RESEARCHGATE, 28 February 2019 (2019-02-28), XP055796300
Attorney, Agent or Firm:
SHENZHEN LUNGTIN LIANDING INTELLECTUAL PROPERTY AGENT LTD. (CN)
Download PDF: