scholarly journals A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection

2021 ◽  
Author(s):  
Xin Wang ◽  
Junichi Yamagishi
Keyword(s):  
Comparative Study ◽  
Synthetic Speech ◽  
Speech Detection

scholarly journals Synthetic speech detection through short-term and long-term prediction traces

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Clara Borrelli ◽  
Paolo Bestagini ◽  
Fabio Antonacci ◽  
Augusto Sarti ◽  
Stefano Tubaro
Keyword(s):  
Deep Learning ◽  
Speech Processing ◽  
Synthetic Speech ◽  
Opinion Formation ◽  
Closed Set ◽  
Speech Detection ◽  
Open Set ◽  
Technological Advances ◽  
Speech Generation ◽  
Long Term Prediction

AbstractSeveral methods for synthetic audio speech generation have been developed in the literature through the years. With the great technological advances brought by deep learning, many novel synthetic speech techniques achieving incredible realistic results have been recently proposed. As these methods generate convincing fake human voices, they can be used in a malicious way to negatively impact on today’s society (e.g., people impersonation, fake news spreading, opinion formation). For this reason, the ability of detecting whether a speech recording is synthetic or pristine is becoming an urgent necessity. In this work, we develop a synthetic speech detector. This takes as input an audio recording, extracts a series of hand-crafted features motivated by the speech-processing literature, and classify them in either closed-set or open-set. The proposed detector is validated on a publicly available dataset consisting of 17 synthetic speech generation algorithms ranging from old fashioned vocoders to modern deep learning solutions. Results show that the proposed method outperforms recently proposed detectors in the forensics literature.

A cross-vocoder study of speaker independent synthetic speech detection using phase information

2014 ◽  
Author(s):  
Jon Sanchez ◽  
Ibon Saratxaga ◽  
Inma Hernaez ◽  
Eva Navas ◽  
Daniel Erro
Keyword(s):  
Synthetic Speech ◽  
Phase Information ◽  
Speech Detection ◽  
Speaker Independent

Significance of Subband Features for Synthetic Speech Detection

2020 ◽  
Vol 15 ◽  
pp. 2160-2170 ◽  
Author(s):  
Jichen Yang ◽  
Rohan Kumar Das ◽  
Haizhou Li
Keyword(s):  
Synthetic Speech ◽  
Speech Detection

scholarly journals A comparison of features for synthetic speech detection

2015 ◽  
Author(s):  
Md. Sahidullah ◽  
Tomi Kinnunen ◽  
Cemal Hanilçi
Keyword(s):  
Synthetic Speech ◽  
Speech Detection

scholarly journals SINTETINĖS ŠNEKOS KOKYBĖS VERTINIMAS: KELIŲ KOMPIUTERINIŲ SINTEZATORIŲ LYGINAMASIS TYRIMAS

Psichologija ◽  
2002 ◽  
Vol 25 ◽  
pp. 72-96 ◽  
Author(s):  
Albinas Bagdonas ◽  
Feliksas Laugalys
Keyword(s):  
Comparative Study ◽  
Speech Intelligibility ◽  
Speech Quality ◽  
Natural Speech ◽  
Synthetic Speech ◽  
Human Speech ◽  
Previous Version ◽  
Computer Based ◽  
Improve Correlation

Straipsnyje pateikiami kelių versijų lietuviškos ir rusiškos sintetinės šnekos suprantamumo ir lietuviškos, rusiškos, vengriškos bei itališkos sintetinių šnekų patrauklumo duomenys. Lietuvių ir rusų diktorių kalba yra suprantamesnė nei atitinkama sintetinė. Ankstesnė rusiškos šnekos sintezė blogesnė nei lietuviška ar patobulinta rusiška sintezė (PRS). Pagal sintetinamų garsų charakteristikas aiškėja dvi priešingos PRS tendencijos - pagal bendrą atpažinimo klaidų mažėjimą ji artėja prie natūralios šnekos, tačiau pagal klaidų homogeniškumą nuo pastarosios tolsta. Kadangi pirmoji tendencija vyrauja, bendra atstojamoji rodo PRS gerėjimą.PRS suprantamumo ir patrauklumo koreliacija taip pat rodo jos didesnį artumą natūraliai šnekai. Tiriamiesiems PRS yra patrauklesnė nei ankstesnė rusiškos sintezės versija. Pastaroji, tiriamųjų nuomone, panašesne į roboto šneką, o PRS - į blogą, tačiau jau žmogaus šnekos versiją.Pagal patrauklumo duomenis natūralią šneką labiausiai vertina vengrų klausytojai, o kritiškiausi jos atžvilgiu yra italai. Visos tirtos sintetinių šnekų versijos vertinamos kaip mažiau patrauklios nei natūrali šneka, tačiau jas patobulinus šis vertinimas švelnėja. EVALUATION OF SYNTHETIC SPEECH QUALITY: A COMPARATIVE STUDY OF SEVERAL COMPUTER-BASED SPEECH SYNTHESIZERS Albinas Bagdonas, Feliksas Laugalys SummaryThis paper examines some versions of Lithuanian and Russian synthetic speech intelligibility and Lithuanian, Russian, Hungarian and Italian synthetic speech acceptability. The speech of both Russian and Lithuanian speaker is more intelligible than Russian or Lithuanian synthesis. Previous version of Russian synthesis is worse than Lithuanian and improved Russian synthesis (IRS). Study of characteristics of IRS sounds shows two opposite tendencies - according to the general quantity of mistake reduction this version is tending towards the natural speech, but according to the homogeneity of mistakes, it moves away. As the first tendency is clearly dominant, the general resultant in the new version shows a tend to improve. Correlation between intelligibility and acceptability of IRS deals possibility of small progress towards the natural speech. The IRS is more acceptable to subjects than previous version. The old synthesis is viewed as a rather decent instance of a robot's speech, while the IRS - as a poor variant of human speech. Acceptability studies showed natural speech more enjoyed by Hungarian listeners and more critical by Italian. All versions of synthetic speech were judged as less acceptable than natural but after improvement most of listeners changed their mind.

scholarly journals Long-term variable Q transform: A novel time-frequency transform algorithm for synthetic speech detection

2021 ◽  
pp. 103256
Author(s):  
Jialong Li ◽  
Hongxia Wang ◽  
Peisong He ◽  
Sani M. Abdullahi ◽  
Bin Li
Keyword(s):  
Synthetic Speech ◽  
Speech Detection ◽  
Time Frequency
Sign in / Sign up

Export Citation Format

Share Document