Real-Time Guitar Amplifier Emulation with Deep Learning

Autor: Alec Wright, Eero-Pekka Damskägg, Lauri Juvela, Vesa Välimäki

Publikováno v: Applied Sciences, Vol 10, Iss 3, p 766 (2020)

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 mo

Externí odkaz: https://doaj.org/article/8b656def159c434093de564c9ff6c719

Exposure Bias and State Matching in Recurrent Neural Network Virtual Analog Models

Autor: Aleksi Peussa, Eero-Pekka Damskägg, Thomas Sherson, Stylianos Mimilakis, Lauri Juvela, Athanasios Gotsopoulos, Vesa Valimaki

Publikováno v: Aalto University

Virtual analog (VA) modeling using neural networks (NNs) has great potential for rapidly producing high-fidelity models. Recurrent neural networks (RNNs) are especially appealing for VA due to their connection with discrete nodal analysis. Furthermor

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::451664f506a91759baf52253775dbb2f
https://doi.org/10.23919/dafx51585.2021.9768259

Normal-to-Lombard adaptation of speech synthesis using long short-term memory recurrent neural networks

Autor: Manu Airaksinen, Cassia Valentini-Botinhao, Paavo Alku, Bajibabu Bollepalli, Lauri Juvela

Publikováno v: Bollepalli, B, Juvela, L, Airaksinen, M, Valentini Botinhao, C & Alku, P 2019, ' Normal-to-Lombard Adaptation of Speech Synthesis Using Long Short-Term Memory Recurrent Neural Networks ', Speech Communication, vol. 110, pp. 64-75 . https://doi.org/10.1016/j.specom.2019.04.008

In this article, three adaptation methods are compared based on how well they change the speaking style of a neural network based text-to-speech (TTS) voice. The speaking style conversion adopted here is from normal to Lombard speech. The selected ad

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f50039939676dd55810a0f02ac055ba3
https://doi.org/10.1016/j.specom.2019.04.008

ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech

Autor: Hirokazu Kameoka, Hsin-Te Hwang, Driss Matrouf, Markus Becker, Quan Wang, Sahidullah, Ye Jia, Yu Zhang, Lauri Juvela, Hsin-Min Wang, Wen-Chin Huang, Zhen-Hua Ling, Yuan Jiang, Yi-Chiao Wu, Héctor Delgado, Massimiliano Todisco, Yu Tsao, Li-Juan Liu, Junichi Yamagishi, Jean-François Bonastre, Tomoki Toda, Nicholas Evans, Robert A. J. Clark, Kai Onuma, Yu-Huai Peng, Sébastien Le Maguer, Avashna Govender, Takashi Kaneda, Andreas Nautsch, Kong Aik Lee, Xin Wang, Srikanth Ronanki, Ville Vestman, Koji Mushika, Ingmar Steiner, Tomi Kinnunen, Fergus Henderson, Jing-Xuan Zhang, Kou Tanaka, Paavo Alku

Publikováno v: Computer Speech and Language
Computer Speech and Language, 2020, 64, pp.101114. ⟨10.1016/j.csl.2020.101114⟩
Wang, X, Yamagishi, J, Todisco, M, Delgado, H, Nautsch, A, Evans, N, Sahidullah, M, Vestman, V, Kinnunen, T, Lee, K A, Juvela, L, Alku, P, Peng, Y-H, Hwang, H-T, Tsao, Y, Wang, H-M, Maguer, S L, Becker, M, Henderson, F, Clark, R, Zhang, Y, Wang, Q, Jia, Y, Onuma, K, Mushika, K, Kaneda, T, Jiang, Y, Liu, L-J, Wu, Y-C, Huang, W-C, Toda, T, Tanaka, K, Kameoka, H, Steiner, I, Matrouf, D, Bonastre, J-F, Govender, A, Ronanki, S, Zhang, J-X & Ling, Z-H 2020, ' ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech ', Computer Speech and Language, vol. 64, 101114 . https://doi.org/10.1016/j.csl.2020.101114
Computer Speech and Language, Elsevier, 2020, 64, pp.101114. ⟨10.1016/j.csl.2020.101114⟩

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." The

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::008166e7f7bcf01a98428755ccc18525
https://hal.science/hal-02945493/document

Conditional Spoken Digit Generation with StyleGAN

Autor: Kasperi Palkama, Lauri Juvela, Alexander Ilin

Publikováno v: INTERSPEECH

This paper adapts a StyleGAN model for speech generation with minimal or no conditioning on text. StyleGAN is a multi-scale convolutional GAN capable of hierarchically capturing data structure and latent variation on multiple spatial (or temporal) le

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aaec026025f9843cb813c2d67e43df21