ACL Findings2024
Wav2SQL: Direct Generalizable Speech-To-SQL Parsing
Huadai Liu, Rongjie Huang, Jinzheng He, Gang Sun, Ran Shen, Xize Cheng, Zhou Zhao
Abstract
Speech-to-SQL (S2SQL) aims to convert spoken questions into SQL queries given relational databases, which has been traditionally implemented in a cascaded manner while facing the following challenges: 1) model training is faced with the major issue of data scarcity, where limited parallel data is available; and 2) the systems should be robust enough to handle diverse out-of-domain speech samples that differ from the source data. In this work, we propose the direct generalizable speech-to-SQL parsing model Wav2SQL which avoids error compounding across cascaded systems. Specifically, 1) to accelerate speech-driven SQL parsing research in the community, we release a large-scale and multi-accent dataset MASpider; 2) leveraging the recent progress in the largescale pre-training, we show that it alleviates the data scarcity issue and allow for direct speechto-SQL parsing; and 3) we include the speech re-programming and gradient reversal classifier techniques to reduce acoustic variance and learned style-agnostic representation, improving generalization to unseen out-of-domain custom data. Experimental results demonstrate that Wav2SQL avoids error compounding and achieves state-of-the-art results by up to 4.7% accuracy improvement over the baseline. 1 2
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer cites FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
- ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer cites wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
- Robust Speech Recognition via Large-Scale Weak Supervision cites wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
- OmniAudio: Generating Spatial Audio from 360-Degree Video cites ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations cites vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
Cited by top-tier papers2
Builds on19
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, Michael AuliNeurIPS 2020 · 9,451 citations
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford, Jong Wook Kim, Tao Xu, Greg Brockman et al.ICML 2023 · 6,966 citations
- Measuring and Relieving the Over-Smoothing Problem for Graph Neural Networks from the Topological ViewDeli Chen, Yankai Lin, Wei Li, Peng Li et al.AAAI 2020 · 1,353 citations
- vq-wav2vec: Self-Supervised Learning of Discrete Speech RepresentationsAlexei Baevski, Steffen Schneider, Michael AuliICLR 2020 · 730 citations
- FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechYi Ren, Chenxu Hu, Xu Tan, Tao Qin et al.ICLR 2021 · 513 citations
Related papers
- S²SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL ParsersBinyuan Hui, Ruiying Geng, Lihan Wang, Bowen Qin et al.ACL Findings 2022 · 66 citations
- Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL ParsingJinyang Li, Binyuan Hui, Reynold Cheng, Bowen Qin et al.AAAI 2023 · 164 citations
- Towards Generalizable and Robust Text-to-SQL ParsingChang Gao, Bowen Li, Wenxuan Zhang, Wai Lam et al.EMNLP Findings 2022 · 9 citations
- Bridging the Generalization Gap in Text-to-SQL Parsing with Schema ExpansionChen Zhao, Yu Su, Adam Pauls, Emmanouil Antonios PlataniosACL 2022 · 19 citations
- Semantic Decomposition of Question and SQL for Text-to-SQL ParsingBen Eyal, Moran Mahabi, Ophir Haroche, Amir Bachar et al.EMNLP Findings 2023 · 7 citations
