webMUSHRA — A Comprehensive Framework for Web-based Listening Tests

Schoeffler, Michael; Bartoschek, Sarah; Stöter, Fabian-Robert; Roess, Marlene; Westphal, Susanne; Edler, Bernd; Herre, Jürgen

doi:10.5334/jors.187

Cited by 149 publications

(82 citation statements)

References 8 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The listening test items consisted of six clips, each approximately 2-4 s long, taken from the validation and test sets of the dataset. The MUSHRA test was carried out using the WebMUSHRA interface [39], shown in Figure 12. For each test the user was presented with the reference and the seven test items.…”

Section: Listening Testsmentioning

confidence: 99%

Real-Time Guitar Amplifier Emulation with Deep Learning

Wright

Damskägg²,

Juvela³

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

This article investigates the use of deep neural networks for black-box modelling of audio distortion circuits, such as guitar amplifiers and distortion pedals. Both a feedforward network, based on the WaveNet model, and a recurrent neural network model are compared. To determine a suitable hyperparameter configuration for the WaveNet, models of three popular audio distortion pedals were created: the Ibanez Tube Screamer, the Boss DS-1, and the Electro-Harmonix Big Muff Pi. It is also shown that three minutes of audio data is sufficient for training the neural network models. Real-time implementations of the neural networks were used to measure their computational load. To further validate the results, models of two valve amplifiers, the Blackstar HT-5 Metal and the Mesa Boogie 5:50 Plus, were created, and subjective tests were conducted. The listening test results show that the models of the first amplifier could be identified as different from the reference, but the sound quality of the best models was judged to be excellent. In the case of the second guitar amplifier, many listeners were unable to hear the difference between the reference signal and the signals produced with the two largest neural network models. This study demonstrates that the neural network models can convincingly emulate highly nonlinear audio distortion circuits, whilst running in real-time, with some models requiring only a relatively small amount of processing power to run on a modern desktop computer.

show abstract

Section: Listening Testsmentioning

confidence: 99%

Real-Time Guitar Amplifier Emulation with Deep Learning

Wright

Damskägg²,

Juvela³

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Similarly, all results of listeners who rate the anchor with more than 90 MUSRHA-points more than 15 % of the time are excluded. We used the webMUSHRA implementation, which is available online and was developed by AudioLabs [47].…”

Section: B Mushra Testmentioning

confidence: 99%

Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding

Schönherr¹,

Kohls²,

Zeiler³

et al. 2019

Proceedings 2019 Network and Distributed System Security Symposium

193

157

View full text Add to dashboard Cite

Voice interfaces are becoming accepted widely as input methods for a diverse set of devices. This development is driven by rapid improvements in automatic speech recognition (ASR), which now performs on par with human listening in many tasks. These improvements base on an ongoing evolution of deep neural networks (DNNs) as the computational core of ASR. However, recent research results show that DNNs are vulnerable to adversarial perturbations, which allow attackers to force the transcription into a malicious output.In this paper, we introduce a new type of adversarial examples based on psychoacoustic hiding. Our attack exploits the characteristics of DNN-based ASR systems, where we extend the original analysis procedure by an additional backpropagation step. We use this backpropagation to learn the degrees of freedom for the adversarial perturbation of the input signal, i.e., we apply a psychoacoustic model and manipulate the acoustic signal below the thresholds of human perception. To further minimize the perceptibility of the perturbations, we use forced alignment to find the best fitting temporal alignment between the original audio sample and the malicious target transcription. These extensions allow us to embed an arbitrary audio input with a malicious voice command that is then transcribed by the ASR system, with the audio signal remaining barely distinguishable from the original signal. In an experimental evaluation, we attack the state-of-the-art speech recognition system Kaldi and determine the best performing parameter and analysis setup for different types of input. Our results show that we are successful in up to 98 % of cases with a computational effort of fewer than two minutes for a ten-second audio file. Based on user studies, we found that none of our target transcriptions were audible to human listeners, who still understand the original speech content with unchanged accuracy.

show abstract

“…To assess how well each of the neural networks emulate the guitar amplifier, a multiple stimuli with hidden reference and anchor (MUSHRA) listening test was conducted [20]. The webMUSHRA interface was used to conduct the tests [21]. For each MUSHRA trial, the participant was presented with an audio clip that had been processed through the guitar amplifier, as well as clips that had been processed by neural network models trained by each of the three loss functions being tested.…”

Section: Listening Testmentioning

confidence: 99%

Perceptual loss function for neural modeling of audio systems

Wright

Välimäki

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This work investigates alternate pre-emphasis filters used as part of the loss function during neural network training for nonlinear audio processing. In our previous work, the errorto-signal ratio loss function was used during network training, with a first-order highpass pre-emphasis filter applied to both the target signal and neural network output. This work considers more perceptually relevant pre-emphasis filters, which include lowpass filtering at high frequencies. We conducted listening tests to determine whether they offer an improvement to the quality of a neural network model of a guitar tube amplifier. Listening test results indicate that the use of an A-weighting pre-emphasis filter offers the best improvement among the tested filters. The proposed perceptual loss function improves the sound quality of neural network models in audio processing without affecting the computational cost.

show abstract

webMUSHRA — A Comprehensive Framework for Web-based Listening Tests

Cited by 149 publications

References 8 publications

Real-Time Guitar Amplifier Emulation with Deep Learning

Real-Time Guitar Amplifier Emulation with Deep Learning

Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding

Perceptual loss function for neural modeling of audio systems

Contact Info

Product

Resources

About