Zobrazeno 1 - 10
of 257
pro vyhledávání: '"Nilsson Mattias"'
As speech processing systems in mobile and edge devices become more commonplace, the demand for unintrusive speech quality monitoring increases. Deep learning methods provide high-quality estimates of objective and subjective speech quality metrics.
Externí odkaz:
http://arxiv.org/abs/2407.04578
Counterfactual explanations (CE) are the de facto method of providing insight and interpretability in black-box decision-making models by identifying alternative input instances that lead to different outcomes. This paper extends the concept of CE to
Externí odkaz:
http://arxiv.org/abs/2401.13112
Autor:
Nilsson, Mattias, Pina, Ton Juny, Khacef, Lyes, Liwicki, Foteini, Chicca, Elisabetta, Sandin, Fredrik
With the expansion of AI-powered virtual assistants, there is a need for low-power keyword spotting systems providing a "wake-up" mechanism for subsequent computationally expensive speech recognition. One promising approach is the use of neuromorphic
Externí odkaz:
http://arxiv.org/abs/2301.09962
Autor:
Nilsson, Mattias, Schelén, Olov, Lindgren, Anders, Bodin, Ulf, Paniagua, Cristina, Delsing, Jerker, Sandin, Fredrik
Publikováno v:
Frontiers in Neuroscience 17 (2023)
Increasing complexity and data-generation rates in cyber-physical systems and the industrial Internet of things are calling for a corresponding increase in AI capabilities at the resource-constrained edges of the Internet. Meanwhile, the resource req
Externí odkaz:
http://arxiv.org/abs/2210.11190
Publikováno v:
7th International Conference on Spoken Language Processing (ICSLP2002), September 16-20, 2002
In this paper, we consider the effect of a bandwidth extension of narrow-band speech signals (0.3-3.4 kHz) to 0.3-8 kHz on speaker verification. Using covariance matrix based verification systems together with detection error trade-off curves, we com
Externí odkaz:
http://arxiv.org/abs/2204.02040
Publikováno v:
2002 11th European Signal Processing Conference, 2002, pp. 1-4
In this paper we discuss the relevance of bandwidth extension for speaker identification tasks. Mainly we want to study if it is possible to recognize voices that have been bandwith extended. For this purpose, we created two different databases (micr
Externí odkaz:
http://arxiv.org/abs/2202.13865
Mixed-signal neuromorphic processors with brain-like organization and device physics offer an ultra-low-power alternative to the unsustainable developments of conventional deep learning and computing. However, realizing the potential of such neuromor
Externí odkaz:
http://arxiv.org/abs/2106.05686
Publikováno v:
2020 International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1-7
Spiking neurons can perform spatiotemporal feature detection by nonlinear synaptic and dendritic integration of presynaptic spike patterns. Multicompartment models of non-linear dendrites and related neuromorphic circuit designs enable faithful imita
Externí odkaz:
http://arxiv.org/abs/2002.04924
Autor:
Sandin, Fredrik, Nilsson, Mattias
Publikováno v:
Frontiers in Neuroscience; Neuromorphic Engineering (2020)
Spiking neural networks implemented in dynamic neuromorphic processors are well suited for spatiotemporal feature detection and learning, for example in ultra low-power embedded intelligence and deep edge applications. Such pattern recognition networ
Externí odkaz:
http://arxiv.org/abs/1906.12282
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.