DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues

TL;DR

DialBGM introduces a new benchmark dataset for evaluating dialogue-conditioned background music recommendation models, highlighting current models' limitations in matching human preferences.

Contribution

The paper presents DialBGM, a benchmark dataset of daily dialogues with music preferences, enabling standardized evaluation of BGM recommendation models in conversational contexts.

Findings

Current models achieve less than 35% Hit@1 accuracy.

DialBGM reveals significant gaps between model predictions and human judgments.

Benchmark facilitates development of discourse-aware BGM selection methods.

Abstract

Selecting an appropriate background music (BGM) that supports natural human conversation is a common production step in media and interactive systems. In this paper, we introduce dialogue-conditioned BGM recommendation, where a model should select non-intrusive, fitting music for a multi-turn conversation that often contains no music descriptors. To study this novel problem, we present DialBGM, a benchmark of 1,200 open-domain daily dialogues, each paired with four candidate music clips and annotated with human preference rankings. Rankings are determined by background suitability criteria, including contextual relevance, non-intrusiveness, and consistency. We evaluate a wide range of open-source and proprietary models, including audio-language models and multimodal LLMs, and show that current models fall far short of human judgments; no model exceeds 35% Hit@1 when selecting the top-ranked clip. DialBGM provides a standardized benchmark for developing discourse-aware methods for BGM selection and for evaluating both retrieval-based and generative models.