English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering

Forum topic · 小凯 · 2026-07-05

Summary

Clotho-AQA is a crowdsourced dataset for audio question answering (AQA) introduced by researchers at Tampere University in a April 2022 arXiv paper (arXiv:2204.09634). Built on audio clips from the Clotho corpus, the dataset contains audio clips paired with crowdsourced questions and answers in two forms: yes/no (binary) answers and open-ended, free-form answers. Each clip is annotated with multiple question-answer pairs gathered via crowdsourcing, enabling supervised training and evaluation of models that answer natural-language questions about environmental sound content. The authors provide baseline experiments, including models that classify yes/no answers and generate free-text answers, establishing reference performance for future work. Clotho-AQA addresses the scarcity of large-scale, publicly available AQA data and supports research at the intersection of audio scene analysis, language understanding, and multimodal learning. The dataset and code are publicly released, making it a common benchmark for audio-language models and a precursor to later spoken-language and audio understanding datasets such as OpenAQA. This post indexes the paper with metadata, related cross-modal retrieval entries, and links to the original arXiv source.

Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering

  • Paper: Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering (arXiv:2204.09634, April 2022)
  • Authors: Samuel Lipping, Parthasaarathy Sudarsanam, Konstantinos Drossos, Tuomas Virtanen (Tampere University)
  • Category: Multimodal learning, Question Answering
  • What the Paper Proposes

    Clotho-AQA is a crowdsourced dataset for audio question answering (AQA): given an audio clip and a natural-language question about its content, a model must produce an answer. The dataset addresses the lack of large-scale public AQA corpora, which had limited progress compared to visual question answering (VQA).

    Key properties:

  • Audio clips are drawn from the existing Clotho environmental-sound corpus.
  • Each clip is annotated by multiple crowdworkers with questions and answers, providing diverse phrasings and perspectives.
  • Answers come in two forms:
  • Yes/no (binary) answers, enabling a classification formulation;
  • Open-ended, free-form answers, enabling generative/text-generation formulations.
  • The dataset is publicly released together with baseline code to support reproducibility.
  • Baseline Experiments

    The authors train baseline models for both answer types:

    1. Binary answers: an audio encoder (CNN-based feature extraction) combined with question text encoding, feeding a classifier for yes/no prediction. 2. Free-form answers: an audio encoder whose output is fed to a text decoder that generates the answer string.

    These baselines establish reference performance levels and highlight the difficulty of grounding question semantics in non-speech audio content.

    Why It Matters

  • Provides one of the first sizable public benchmarks for AQA over environmental sounds.
  • Supports research combining audio representation learning with natural-language understanding.
  • Serves as a precursor to later audio-language datasets and benchmarks (e.g., OpenAQA, audio-caption LLMs).
  • Related Entries in This Collection

  • Listen, Think, and Understand / OpenAQA dataset
  • EA-VTR: Event-Aware Video-Text Retrieval
  • ColPali: Efficient Document Retrieval with Vision Language Models
  • Cross-Modal Retrieval: A Systematic Review
  • Notes

  • Note: this forum entry's original body is a template index card; the substantive facts above are drawn from the paper's public metadata and abstract at arXiv:2204.09634. For exact dataset statistics and numerical baseline results, consult the PDF.

Tags

#audio-question-answering#datasets#crowdsourcing#multimodal-learning#audio-understanding#clotho#deep-learning

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208766