Sound Reasoning (Literally): Prospects and Challenges of Current Acoustic Logics

Champagne, Marc

doi:10.1007/s11787-015-0127-7

Cited by 16 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Richard Feynman, for example, famously claimed to "listen" to his imagination. For more on the role of sound in formal logic, see Pietarinen (2010) and Champagne (2015b). For more on the role of sound in informal logic, see Groarke (2018).…”

Section: …But Moving Ones Mightmentioning

confidence: 99%

Why Images Cannot be Arguments, But Moving Ones Might

Champagne

Pietarinen

2019

Argumentation

Self Cite

View full text Add to dashboard Cite

Some have suggested that images can be arguments. Images can certainly bolster the acceptability of individual premises. We worry, though, that the static nature of images prevents them from ever playing a genuinely argumentative role. To show this, we call attention to a dilemma. The conclusion of a visual argument will either be explicit or implicit. If a visual argument includes its (explicit) conclusion, then that conclusion must be demarcated from the premise(s) or otherwise the argument will beg the question. If a visual argument does not include its (implicit) conclusion, then the premises on display must license that specific conclusion and not its opposite, in accordance with some demonstrable rationale. We show how major examples from the literature fail to escape this dilemma. Drawing inspiration from the graphical logic of C. S. Peirce, we suggest instead that images can be manipulated (erased, dragged, copied, etc.) in a way that overcomes the dilemma. Diagrammatic reasoning can take one stepwise from an initial visual layout to a conclusion-thereby providing a principled rationale that bars opposite conclusions-and the visual inscription of this correct conclusion can come afterward in time-thereby distinguishing the conclusion from the premises. Even though this practical application of Peirce's logical ideas to informal contexts requires that one make adjustments, we believe it points to a dynamic conception of visual argumentation that will prove more fertile in the long run.

show abstract

Section: …But Moving Ones Mightmentioning

confidence: 99%

Why Images Cannot be Arguments, But Moving Ones Might

Champagne

Pietarinen

2019

Argumentation

Self Cite

View full text Add to dashboard Cite

show abstract

“…In most studies, reasoning is supported by spatial and symbolic representations in the visual domain [21,22]. However, reasoning and logic relationships can also be studied via representations of sounds [23]. Including the auditory modality in studies on reasoning is of particular interest for research in artificial intelligence [24], but also has implications in real world applications [25].…”

Section: Introductionmentioning

confidence: 99%

NAAQA: A Neural Architecture for Acoustic Question Answering

Abdelnour

Rouat

Salvi

2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

The goal of the Acoustic Question Answering (AQA) task is to answer a free-form text question about the content of an acoustic scene. It was inspired by the Visual Question Answering (VQA) task. In this paper, based on the previously introduced CLEAR dataset, we propose a new benchmark for AQA, namely CLEAR2, that emphasizes the specific challenges of acoustic inputs. These include handling of variable duration scenes, and scenes built with elementary sounds that differ between training and test set. We also introduce NAAQA, a neural architecture that leverages specific properties of acoustic inputs. The use of 1D convolutions in time and frequency to process 2D spectro-temporal representations of acoustic content shows promising results and enables reductions in model complexity. We show that time coordinate maps augment temporal localization capabilities which enhance performance of the network by ∼17 percentage points. On the other hand, frequency coordinate maps have little influence on this task. NAAQA achieves 79.5% of accuracy on the AQA task with ∼4 times fewer parameters than the previously explored VQA model. We evaluate the performance of NAAQA on an independent data set reconstructed from DAQA. We also test the addition of a MALiMo module in our model on both CLEAR2 and DAQA. We provide a detailed analysis of the results for the different question types. We release the code to produce CLEAR2 as well as NAAQA to foster research in this newly emerging machine learning task.

show abstract

“…But reasoning and logic relationships are not attached and bounded exclusively to visual representations. They can be studied via representations of sounds [23]. This is of particular interest for research in artificial intelligence, and has also implications in real world applications [24].…”

Section: Introduction and Related Workmentioning

confidence: 99%

From Visual to Acoustic Question Answering

Abdelnour,

Salvi,

Rouat

2019

Preprint

View full text Add to dashboard Cite

We introduce the new task of Acoustic Question Answering (AQA) to promote research in acoustic reasoning. The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds. The kind of relational questions asked, require that the models perform non-trivial reasoning in order to answer correctly. Although similar problems have been extensively studied in the domain of visual reasoning, we are not aware of any previous studies addressing the problem in the acoustic domain. We propose a method for generating the acoustic scenes from elementary sounds and a number of relevant questions for each scene using templates. We also present preliminary results obtained with two models (FiLM and MAC) that have been shown to work for visual reasoning.

show abstract

Sound Reasoning (Literally): Prospects and Challenges of Current Acoustic Logics

Cited by 16 publications

References 9 publications

Why Images Cannot be Arguments, But Moving Ones Might

Why Images Cannot be Arguments, But Moving Ones Might

NAAQA: A Neural Architecture for Acoustic Question Answering

From Visual to Acoustic Question Answering

Contact Info

Product

Resources

About