LEMONS: Listenable Explanations for Music recOmmeNder Systems

Melchiorre, Alessandro B.; Haunschmid, Verena; Schedl, Markus; Widmer, Gerhard

doi:10.1007/978-3-030-72240-1_60

Cited by 6 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One line of work proposes listenable explanations [10], inspired from radio shows in which hosts provide information about played tracks for creating transitions. Alternatively, item parts such as track snippets focusing on a particular audio source (e. g., instrument or voice [72]) can be emphasized as reasons for recommendation.…”

Section: Overview Of Explanation Methods For Mrssmentioning

confidence: 99%

“…Other than textual modalities, explanations in MRSs include displaying album covers, which may convey information about the style or even allow to recognize record labels (e. g., Deutsche Grammophon, Blue Note). Short audio thumbnails are also a promising way to provide explanations that cannot be otherwise expressed with words [72].…”

Section: Example-based Explanationsmentioning

confidence: 99%

See 1 more Smart Citation

Explainability in Music Recommender Systems

Afchar¹,

Melchiorre²,

Schedl³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The most common way to listen to recorded music nowadays is via streaming platforms which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs, the integration of Music Recommender Systems (MRSs) has become essential. Current real-world MRSs are often quite complex and optimized for recommendation accuracy. They combine several building blocks based on collaborative filtering and content-based recommendation. This complexity can hinder the ability to explain recommendations to end users, which is particularly important for recommendations perceived as unexpected or inappropriate.While pure recommendation performance often correlates with user satisfaction, explainability has a positive impact on other factors such as trust and forgiveness, which are ultimately essential to maintain user loyalty.In this article, we discuss how explainability can be addressed in the context of MRSs. We provide perspectives on how explainability could improve music recommendation algorithms and enhance user experience. First, we review common dimensions and goals of recommenders' explainability and in general of eXplainable Artificial Intelligence (XAI), and elaborate on the extent to which these apply -or need to be adapted -to the specific characteristics of music consumption and recommendation. Then, we show how explainability components can be integrated within a MRS and in what form explanations can be provided. Since the evaluation of explanation quality is decoupled from pure accuracy-based evaluation criteria, we also discuss requirements and strategies for evaluating explanations of music recommendations. Finally, we describe the current challenges for introducing explainability within a large-scale industrial music recommender system and provide research perspectives.

show abstract

Section: Overview Of Explanation Methods For Mrssmentioning

confidence: 99%

Section: Example-based Explanationsmentioning

confidence: 99%

Explainability in Music Recommender Systems

Afchar¹,

Melchiorre²,

Schedl³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…SLIME was demonstrated on the task of singing voice detection [18] and used for analysing a replay spoofing detection system [6]. Haunschmid et al used other types of interpretable features (super pixels [7], source sep-aration estimates [8,9]) for explaining the predictions of a variety of models, including music taggers [8,9] and a content-based music recommender system [10]. Mishra et al [11] proposed different content types for replacing the "grayed out" segments (e.g.…”

Section: Local Interpretable Model-agnostic Explanationsmentioning

confidence: 99%

“…A plethora of explanation methods ("explainers") have been originally developed for text or image data and adapted to the audio domain [1,2], or specifically introduced for MIR systems [3]. Most notably, different versions of Local Interpretable Model-agnostic Explanations (LIME), a posthoc explainer [4], have been used to explain models in a variety of MIR tasks [5][6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples

Praher¹,

Prinz²,

Flexer³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Local explanation methods such as LIME have become popular in MIR as tools for generating post-hoc, model-agnostic explanations of a model's classification decisions. The basic idea is to identify a small set of humanunderstandable features of the classified example that are most influential on the classifier's prediction. These are then presented as an explanation. Evaluation of such explanations in publications often resorts to accepting what matches the expectation of a human without actually being able to verify if what the explanation shows is what really caused the model's prediction. This paper reports on targeted investigations where we try to get more insight into the actual veracity of LIME's explanations in an audio classification task. We deliberately design adversarial examples for the classifier, in a way that gives us knowledge about which parts of the input are potentially responsible for the model's (wrong) prediction. Asking LIME to explain the predictions for these adversaries permits us to study whether local explanations do indeed detect these regions of interest. We also look at whether LIME is more successful in finding perturbations that are more prominent and easily noticeable for a human. Our results suggest that LIME does not necessarily manage to identify the most relevant input features and hence it remains unclear whether explanations are useful or even misleading. * Equal contribution.

show abstract

“…Previous work on interpretability in MIR has dealt with tasks such as music tagging using self-attention [4] and transcription using invertible neural networks [5], and post-hoc explanations for music content analysis have been used to understand what a genre classifier [6] or a singing voice detector [7][8][9][10][11] have learnt. More recently, audioLIME has been proposed [12,13] and has shown promise in explaining tagging models [14] as well as recommendation models [15].…”

Section: Introductionmentioning

confidence: 99%

Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities

Chowdhury,

Praher,

Widmer

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Music emotion recognition is an important task in MIR (Music Information Retrieval) research. Owing to factors like the subjective nature of the task and the variation of emotional cues between musical genres, there are still significant challenges in developing reliable and generalizable models. One important step towards better models would be to understand what a model is actually learning from the data and how the prediction for a particular input is made. In previous work, we have shown how to derive explanations of model predictions in terms of spectrogram image segments that connect to the high-level emotion prediction via a layer of easily interpretable perceptual features. However, that scheme lacks intuitive musical comprehensibility at the spectrogram level. In the present work, we bridge this gap by merging audioLIMEa source-separation based explainer -with mid-level perceptual features, thus forming an intuitive connection chain between the input audio and the output emotion predictions. We demonstrate the usefulness of this method by applying it to debug a biased emotion prediction model.

show abstract

LEMONS: Listenable Explanations for Music recOmmeNder Systems

Cited by 6 publications

References 20 publications

Explainability in Music Recommender Systems

Explainability in Music Recommender Systems

On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples

Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities

Contact Info

Product

Resources

About