Several studies have proposed deep-learning-based models to predict the mean opinion score (MOS) of synthesized speech, showing the possibility of replacing human raters. However, inter- and intra-rater variability in MOSs makes it hard to ensure the high performance of the models. In this paper, we propose a multi-task learning (MTL) method to improve the performance of a MOS prediction model using the following two auxiliary tasks: spoofing detection (SD) and spoofing type classification (STC). Besides, we use the focal loss to maximize the synergy between SD and STC for MOS prediction. Experiments using the MOS evaluation results of the Voice Conversion Challenge 2018 show that proposed MTL with two auxiliary tasks improves MOS prediction. Our proposed model achieves up to 11.6% relative improvement in performance over the baseline model.
Enhancing Anti-spoofing Countermeasures Robustness through Joint Optimization and Transfer Learning
Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi（山梨大学医学、工学和农学综合研究生院）；Duke Kunshan University（昆山杜克大学）；School of Computer Science, Wuhan University（武汉大学计算机学院）
University of Eastern Finland（东芬兰大学）；Queen Mary University of London（伦敦玛丽女王大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学及其应用实验室）；National University of Singapore（新加坡国立大学）
Voice anti-spoofing aims at classifying a given utterance either as a bonafide human sample, or a spoofing attack (e.g. synthetic or replayed sample). Many anti-spoofing methods have been proposed but most of them fail to generalize across domains (corpora) -- and we do not know \emph{why}. We outline a novel interpretative framework for gauging the impact of data quality upon anti-spoofing performance. Our within- and between-domain experiments pool data from seven public corpora and three anti-spoofing methods based on Gaussian mixture and convolutive neural network models. We assess the imp…
The automatic speaker verification spoofing (ASVspoof) challenge series is crucial for enhancing the spoofing consideration and the countermeasures growth. Although the recent ASVspoof 2019 validation results indicate the significant capability to identify most attacks, the model's recognition effect is still poor for some attacks. This paper presents the Online Hard Example Mining (OHEM) algorithm for detecting unknown voice spoofing attacks. The OHEM is utilized to overcome the imbalance between simple and hard samples in the dataset. The presented system provides an equal error rate (EER) o…
Center for Language and Speech Processing, Johns Hopkins UniversityUSA（约翰霍普金斯大学语言与语音处理中心）；Carnegie Mellon UniversityUSA（卡内基梅隆大学）；Data Science and AI Institute (DSAI), Johns Hopkins UniversityUSA（约翰霍普金斯大学数据科学与人工智能研究院）
University of Rochester（罗切斯特大学）；Beijing Institute of Technology（北京理工大学）
Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion. Recently, researchers developed anti-spoofing techniques to improve the reliability of ASV systems against spoofing attacks. However, most methods encounter difficulties in detecting unknown attacks in practical use, which often have different statistical distributions from known attacks. Especially, the fast development of synthetic voice spoofing algorithms is g…
University of Eastern Finland（东芬兰大学）；Bursa Technical University（布尔萨技术大学）
Automatic speaker verification (ASV) technology is recently finding its way to end-user applications for secure access to personal data, smart services or physical facilities. Similar to other biometric technologies, speaker verification is vulnerable to spoofing attacks where an attacker masquerades as a particular target speaker via impersonation, replay, text-to-speech (TTS) or voice conversion (VC) techniques to gain illegitimate access to the system. We focus on TTS and VC that represent the most flexible, high-end spoofing attacks. Most of the prior studies on synthesized or converted sp…
With the rapid development of speech conversion and speech synthesis algorithms, automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. In recent years, researchers had proposed a number of anti-spoofing methods based on hand-crafted features. However, using hand-crafted features rather than raw waveform will lose implicit information for anti-spoofing. Inspired by the promising performance of ConvNeXt in image classification tasks, we revise the ConvNeXt network architecture and propose a lightweight end-to-end anti-spoofing model. By integrating with the channel att…
EURECOM（欧洲通信学院）；National Institute of Informatics（情报通信研究机构）；University of Eastern Finland（东芬兰大学）；Nuance Communications（Nuance通信公司）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛里亚实验室）
The ASVspoof initiative was conceived to spearhead research in anti-spoofing for automatic speaker verification (ASV). This paper describes the third in a series of bi-annual challenges: ASVspoof 2019. With the challenge database and protocols being described elsewhere, the focus of this paper is on results and the top performing single and ensemble system submissions from 62 teams, all of which out-perform the two baseline systems, often by a substantial margin. Deeper analyses shows that performance is dominated by specific conditions involving either specific spoofing attacks or specific ac…
Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware features are a possible solution to this problem. Most successful methods in both challenges focus on spoof-aware features, rather than focusing on a powerful classifier. In this paper we present a novel raw waveform based deep model for spoofing detection, which jointly acts as a feature extractor and classifier, thus allowing it to directly classify speech signa…
Self-supervised speech model is a rapid progressing research topic, and many pre-trained models have been released and used in various down stream tasks. For speech anti-spoofing, most countermeasures (CMs) use signal processing algorithms to extract acoustic features for classification. In this study, we use pre-trained self-supervised speech models as the front end of spoofing CMs. We investigated different back end architectures to be combined with the self-supervised front end, the effectiveness of fine-tuning the front end, and the performance of using different pre-trained self-supervise…
Singapore University of Technology and Design（新加坡科技设计大学）；Tencent Music Entertainment（腾讯音乐娱乐集团）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）
Automatic speaker verification, like every other biometric system, is vulnerable to spoofing attacks. Using only a few minutes of recorded voice of a genuine client of a speaker verification system, attackers can develop a variety of spoofing attacks that might trick such systems. Detecting these attacks using the audio cues present in the recordings is an important challenge. Most existing spoofing detection systems depend on knowing the used spoofing technique. With this research, we aim at overcoming this limitation, by examining robust audio features, both traditional and those learned thr…
National Institute of Informatics（日本国立信息学研究所）；University of Edinburgh（爱丁堡大学）；EURECOM（法国通信系统工程师学校）；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；University of Eastern Finland（东芬兰大学）
Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is vulnerable to spoofing, also referred to as "presentation attacks." These vulnerabilities are generally unacceptable and call for spoofing countermeasures or "presentation attack detection" systems. In addition to impersonation, ASV systems are vulnerable to replay, speech synthesis, and voice conversion attacks. The ASVspoof 2019 edition is the first to consider all three spoofing attack types within a single challen…
National Taiwan University（台湾大学）；Academia Sinica（中央研究院）；The Chinese University of Hong Kong（香港中文大学）
The past few years have witnessed the significant advances of speech synthesis and voice conversion technologies. However, such technologies can undermine the robustness of broadly implemented biometric identification models and can be harnessed by in-the-wild attackers for illegal uses. The ASVspoof challenge mainly focuses on synthesized audios by advanced speech synthesis and voice conversion models, and replay attacks. Recently, the first Audio Deep Synthesis Detection challenge (ADD 2022) extends the attack scenarios into more aspects. Also ADD 2022 is the first challenge to propose the p…
Parallel Stacked Aggregated Network for Voice Authentication in IoT-Enabled Smart Devices
School of Engineering and Computer Science, Oakland University（奥克兰大学工程与计算机科学学院）；College of Innovation and Technology, University of Michigan-Flint（密歇根大学弗林特分校创新与技术学院）；Oakland University（奥克兰大学）；University of Michigan-Flint（密歇根大学弗林特分校）
The threat of spoofing can pose a risk to the reliability of automatic speaker verification. Results from the bi-annual ASVspoof evaluations show that effective countermeasures demand front-ends designed specifically for the detection of spoofing artefacts. Given the diversity in spoofing attacks, ensemble methods are particularly effective. The work in this paper shows that a bank of very simple classifiers, each with a front-end tuned to the detection of different spoofing attacks and combined at the score level through non-linear fusion, can deliver superior performance than more sophistica…
National University of Singapore（新加坡国立大学）；University of Eastern Finland（东芬兰大学）；Nagoya University（名古屋大学）；University of Science and Technology of China（中国科学技术大学）；National Institute of Informatics（国立信息学研究所）
The Voice Conversion Challenge 2020 is the third edition under its flagship that promotes intra-lingual semiparallel and cross-lingual voice conversion (VC). While the primary evaluation of the challenge submissions was done through crowd-sourced listening tests, we also performed an objective assessment of the submitted systems. The aim of the objective assessment is to provide complementary performance analysis that may be more beneficial than the time-consuming listening tests. In this study, we examined five types of objective assessments using automatic speaker verification (ASV), neural …
Spectrograms - time-frequency representations of audio signals - have found widespread use in neural network-based spoofing detection. While deep models are trained on the fullband spectrum of the signal, we argue that not all frequency bands are useful for these tasks. In this paper, we systematically investigate the impact of different subbands and their importance on replay spoofing detection on two benchmark datasets: ASVspoof 2017 v2.0 and ASVspoof 2019 PA. We propose a joint subband modelling framework that employs n different sub-networks to learn subband specific features. These are la…
Speech synthesis methods can create realistic-sounding speech, which may be used for fraud, spoofing, and misinformation campaigns. Forensic methods that detect synthesized speech are important for protection against such attacks. Forensic attribution methods provide even more information about the nature of synthesized speech signals because they identify the specific speech synthesis method (i.e., speech synthesizer) used to create a speech signal. Due to the increasing number of realistic-sounding speech synthesizers, we propose a speech attribution method that generalizes to new synthesize…
National Institute of Informatics（国立信息学研究所）；EURECOM（欧洲通信学院）
Automatic speaker verification is susceptible to various manipulations and spoofing, such as text-to-speech synthesis, voice conversion, replay, tampering, adversarial attacks, and so on. We consider a new spoofing scenario called "Partial Spoof" (PS) in which synthesized or transformed speech segments are embedded into a bona fide utterance. While existing countermeasures (CMs) can detect fully spoofed utterances, there is a need for their adaptation or extension to the PS scenario. We propose various improvements to construct a significantly more accurate CM that can detect and locate short-…
A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria. We contribute to this effort with a comparative perspective in this study. Our comparison of countermeasure models on the ASVspoof 2019 logical access task takes into account recently proposed margin-based training criteria, widely used front ends, and common strategies to deal with varied-length input trials. We also measured intra-model differences through multiple training-evaluation rounds with random initialization. Our statistical analysis demon…
An automatic speaker verification system aims to verify the speaker identity of a speech signal. However, a voice conversion system could manipulate a person's speech signal to make it sound like another speaker's voice and deceive the speaker verification system. Most countermeasures for voice conversion-based spoofing attacks are designed to discriminate bona fide speech from spoofed speech for speaker verification systems. In this paper, we investigate the problem of source speaker identification -- inferring the identity of the source speaker given the voice converted speech. To perform so…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure Speech（微软Azure语音）
Mean opinion score (MOS) is a popular subjective metric to assess the quality of synthesized speech, and usually involves multiple human judges to evaluate each speech utterance. To reduce the labor cost in MOS test, multiple methods have been proposed to automatically predict MOS scores. To our knowledge, for a speech utterance, all previous works only used the average of multiple scores from different judges as the training target and discarded the score of each individual judge, which did not well exploit the precious MOS training data. In this paper, we propose MBNet, a MOS predictor with …
While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based assessment models and shown the potential to automate the speech quality assessment. To improve the previously proposed assessment model, MOSNet, we propose three models using cluster-based modeling methods: using a global quality token (GQT) layer, using an Encoding Layer, and using both of them. We perform experiments using the evaluation results of the Voice Conv…
Text-to-speech and voice conversion studies are constantly improving to the extent where they can produce synthetic speech almost indistinguishable from bona fide human speech. In this regard, the importance of countermeasures (CM) against synthetic voice attacks of the automatic speaker verification (ASV) systems emerges. Nonetheless, most end-to-end spoofing detection networks are black-box systems, and the answer to what is an effective representation for finding artifacts remains veiled. In this paper, we examine which feature space can effectively represent synthetic artifacts using wav2v…
With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in the model creation process is obtaining a sufficient amount of training data. In this paper, we explore the effectiveness of synthesized speech data in training small, spoken term detection models of around 400k parameters. Instead of training such models directly on the audio or low level features such as MFCCs, we use a pre-trained speech embedding model trained to extract u…
Existing approaches for replay and synthetic speech detection still lack generalizability to unseen spoofing attacks. This work proposes to leverage a novel model structure, so-called Res2Net, to improve the anti-spoofing countermeasure's generalizability. Res2Net mainly modifies the ResNet block to enable multiple feature scales. Specifically, it splits the feature maps within one block into multiple channel groups and designs a residual-like connection across different channel groups. Such connection increases the possible receptive fields, resulting in multiple feature scales. This multiple…
We have been working on speech synthesis for rakugo (a traditional Japanese form of verbal entertainment similar to one-person stand-up comedy) toward speech synthesis that authentically entertains audiences. In this paper, we propose a novel evaluation methodology using synthesized rakugo speech and real rakugo speech uttered by professional performers of three different ranks. The naturalness of the synthesized speech was comparable to that of the human speech, but the synthesized speech entertained listeners less than the performers of any rank. However, we obtained some interesting insight…
Modern text-to-speech (TTS) and voice conversion (VC) systems produce natural sounding speech that questions the security of automatic speaker verification (ASV). This makes detection of such synthetic speech very important to safeguard ASV systems from unauthorized access. Most of the existing spoofing countermeasures perform well when the nature of the attacks is made known to the system during training. However, their performance degrades in face of unseen nature of attacks. In comparison to the synthetic speech created by a wide range of TTS and VC methods, genuine speech has a more consis…
