Abstract
In Spoken Question Answering (SQA), automatic speech recognition (ASR) outputs are often relayed to language models for QA. However, constructing such a cascaded framework with large language models (LLMs) in a real-time SQA setting involves realistic challenges, such as noise in the ASR output, the limited context length of LLMs, and latency in processing large models. This paper proposes a novel model-agnostic framework, RT-VQ2A2, to address these challenges. RT-VQ2A2 consists of three steps: codebook preparation, quantized semantic vector extractor, and dual segment selector. We construct a codebook from clustering, removing outliers on a text corpus derived from ASR to mitigate the influence of ASR error. Extracting quantized semantic vectors through a pre-built codebook shows significant speed and performance improvements in relevant context retrieval. Dual segment selector considers both semantic and lexical aspects to deal with ASR error. The efficacy of RT-VQ2A2 is validated on the widely used Spoken-SQuAD dataset.- Anthology ID:
- 2024.lrec-main.1238
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 14204–14214
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1238
- DOI:
- Cite (ACL):
- Kyungho Kim, Seongmin Park, and Jihwa Lee. 2024. RT-VQ2A2: Real Time Vector Quantized Question Answering with ASR. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14204–14214, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- RT-VQ2A2: Real Time Vector Quantized Question Answering with ASR (Kim et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1238.pdf