Principles of Psychoacoustics

Lin, Yiqing; Abdulla, Waleed H.

doi:10.1007/978-3-319-07974-5_2

Cited by 25 publications

(23 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we performed LP analysis with P = 11.

The extraction of PLP features depends on three psychoacoustic principles of hearing [ 32 ]: (1) critical bandwidth, (2) equal-loudness hearing curve, and (3) intensity loudness power law of hearing. The critical bandwidths are computed by applying the Bark-scale proposed by Zwicker [ 33 ].…”

Section: Evaluation Of the Avpdmentioning

confidence: 99%

Development of the Arabic Voice Pathology Database and Its Evaluation by Using Speech Features and Machine Learning Algorithms

Mesallam

Farahat

Malki

et al. 2017

Journal of Healthcare Engineering

View full text Add to dashboard Cite

A voice disorder database is an essential element in doing research on automatic voice disorder detection and classification. Ethnicity affects the voice characteristics of a person, and so it is necessary to develop a database by collecting the voice samples of the targeted ethnic group. This will enhance the chances of arriving at a global solution for the accurate and reliable diagnosis of voice disorders by understanding the characteristics of a local group. Motivated by such idea, an Arabic voice pathology database (AVPD) is designed and developed in this study by recording three vowels, running speech, and isolated words. For each recorded samples, the perceptual severity is also provided which is a unique aspect of the AVPD. During the development of the AVPD, the shortcomings of different voice disorder databases were identified so that they could be avoided in the AVPD. In addition, the AVPD is evaluated by using six different types of speech features and four types of machine learning algorithms. The results of detection and classification of voice disorders obtained with the sustained vowel and the running speech are also compared with the results of an English-language disorder database, the Massachusetts Eye and Ear Infirmary (MEEI) database.

show abstract

“…In this study, we performed LP analysis with P = 11.

Section: Evaluation Of the Avpdmentioning

confidence: 99%

Development of the Arabic Voice Pathology Database and Its Evaluation by Using Speech Features and Machine Learning Algorithms

Mesallam

Farahat

Malki

et al. 2017

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…The first objective is to estimate an attack that fools the network (with the same as in equation 2). The second objective uses a psychoacoustic model to make the adversarial perturbation imperceptible due to frequency masking [31]. The detailed equations solving the optimization process are presented in [16].…”

Section: Adversarial Attacksmentioning

confidence: 99%

Adversarial Attacks and Defenses for Speech Recognition Systems

Żelasko¹,

Joshi²,

Shao³

et al. 2021

Preprint

View full text Add to dashboard Cite

The ubiquitous presence of machine learning systems in our lives necessitates research into their vulnerabilities and appropriate countermeasures. In particular, we investigate the effectiveness of adversarial attacks and defenses against automatic speech recognition (ASR) systems. We select two ASR models -a thoroughly studied DeepSpeech model and a more recent Espresso framework Transformer encoder-decoder model. We investigate two threat models: a denial-of-service scenario where fast gradient-sign method (FGSM) or weak projected gradient descent (PGD) attacks are used to degrade the model's word error rate (WER); and a targeted scenario where a more potent imperceptible attack forces the system to recognize a specific phrase. We find that the attack transferability across the investigated ASR systems is limited. To defend the model, we use two preprocessing defenses: randomized smoothing and WaveGAN-based vocoder, and find that they significantly improve the model's adversarial robustness. We show that a WaveGAN vocoder can be a useful countermeasure to adversarial attacks on ASR systems -even when it is jointly attacked with the ASR, the target phrases' word error rate is high.

show abstract

“…Here x is an audio sample, S mag is its magnitude spectrum and M is the matrix of the corresponding masking thresholds. For more details, interested readers can refer to Lin and Abdulla (2015).…”

Section: Variable Perceptionmentioning

confidence: 99%

Beyond $L_p$ clipping: Equalization-based Psychoacoustic Attacks against ASRs

Abdullah¹,

Rahman²,

Peeters³

et al. 2021

Preprint

View full text Add to dashboard Cite

Automatic Speech Recognition (ASR) systems convert speech into text and can be placed into two broad categories: traditional and fully end-to-end. Both types have been shown to be vulnerable to adversarial audio examples that sound benign to the human ear but force the ASR to produce malicious transcriptions. Of these attacks, only the "psychoacoustic" attacks can create examples with relatively imperceptible perturbations, as they leverage the knowledge of the human auditory system. Unfortunately, existing psychoacoustic attacks can only be applied against traditional models, and are obsolete against the newer, fully end-to-end ASRs. In this paper, we propose an equalization-based psychoacoustic attack that can exploit both traditional and fully end-to-end ASRs. We successfully demonstrate our attack against real-world ASRs that include DeepSpeech and Wav2Letter. Moreover, we employ a user study to verify that our method creates low audible distortion. Specifically, 80 of the 100 participants voted in favor of all our attack audio samples as less noisier than the existing state-of-the-art attack. Through this, we demonstrate both types of existing ASR pipelines can be exploited with minimum degradation to attack audio quality.

show abstract

Principles of Psychoacoustics

Cited by 25 publications

References 10 publications

Development of the Arabic Voice Pathology Database and Its Evaluation by Using Speech Features and Machine Learning Algorithms

Development of the Arabic Voice Pathology Database and Its Evaluation by Using Speech Features and Machine Learning Algorithms

Adversarial Attacks and Defenses for Speech Recognition Systems

Beyond $L_p$ clipping: Equalization-based Psychoacoustic Attacks against ASRs

Contact Info

Product

Resources

About