# A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering

arXiv: https://arxiv.org/abs/2409.13483 · HTML: https://mlsanity.com/paper/2409.13483/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension](https://mlsanity.com/paper/1804.00320/) (2018)
- [SD-QA: Spoken Dialectal Question Answering for the Real World](https://mlsanity.com/paper/2109.12072/) (2021)
- [Knowledge Distillation for Improved Accuracy in Spoken Question Answering](https://mlsanity.com/paper/2010.11067/) (2020)
- [NoiseQA: Challenge Set Evaluation for User-Centric Question Answering](https://mlsanity.com/paper/2102.08345/) (2021)
- [Dealing with Typos for BERT-based Passage Retrieval and Ranking](https://mlsanity.com/paper/2108.12139/) (2021)
- [Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings](https://mlsanity.com/paper/2205.02303/) (2022)
- [CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos](https://mlsanity.com/paper/2204.00716/) (2022)
- [On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering](https://mlsanity.com/paper/2209.12944/) (2022)
- [Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems](https://mlsanity.com/paper/2005.08742/) (2020)

## Built on by (most cited first, 2 of 2)

- [SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise](https://mlsanity.com/paper/2602.12783/) (2026)
- [V=akQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering](https://mlsanity.com/paper/2609.19879/) (2026)

## Abstract (arXiv)

Speech-based open-domain question answering (QA over a large corpus of text passages with spoken questions) has emerged as an important task due to the increasing number of users interacting with QA systems via speech interfaces. Passage retrieval is a key task in speech-based open-domain QA. So far, previous works adopted pipelines consisting of an automatic speech recognition (ASR) model that transcribes the spoken question before feeding it to a dense text retriever. Such pipelines have several limitations. The need for an ASR model limits the applicability to low-resource languages and specialized domains with no annotated speech data. Furthermore, the ASR model propagates its errors to the retriever. In this work, we try to alleviate these limitations by proposing an ASR-free, end-to-end trained multimodal dense retriever that can work directly on spoken questions. Our experimental results showed that, on shorter questions, our retriever is a promising alternative to the textitASR and Retriever pipeline, achieving better retrieval performance in cases where ASR would have mistranscribed important words in the question or have produced a transcription with a high word error rate.