Speechbert: An Audio-and-text Jointly Learned Language Model For End-to-end Spoken Question Answering

Abstract

While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning from the very successful BERT model for various text processing tasks, here we proposed an audio-and-text jointly learned SpeechBERT model. This model outperformed the conventional approach of cascading ASR with the following text question answering (TQA) model on datasets including ASR errors in answer spans, because the end-to-end model was shown to be able to extract information out of audio data before ASR produced errors. When ensembling the proposed end-to-end model with the cascade architecture, even better performance was achieved. In addition to the potential of end-to-end SQA, the SpeechBERT can also be considered for many other spoken language understanding tasks just as BERT for many text processing tasks.

Stats

• citations43
• S2 citations—
• github stars0
• HF likes0
• heat score12.33
• arxiv keychuang2019speechbert

Related papers

• End-to-end Contrastive Language-speech Pretraining Model For Long-form Spoken Question Answering (2025)0.00
• Self-supervised Contrastive Cross-modality Representation Learning For Spoken Question Answering (2021)9.41
• Speechdpr: End-to-end Spoken Passage Retrieval For Open-domain Spoken Question Answering (2024)0.00
• Mitigating The Impact Of Speech Recognition Errors On Spoken Question Answering By Adversarial Domain Adaptation (2019)6.77
• Wabert: A Low-resource End-to-end Model For Spoken Language Understanding And Speech-to-bert Alignment (2022)0.00
• Sviqa: A Unified Speech-vision Multimodal Model For Textless Visual Question Answering (2025)0.00
• ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding (2020)9.59
• Spoken Question Answering And Speech Continuation Using Spectrogram-powered LLM (2023)2.76