Knowledge Distillation for Improved Accuracy in Spoken Question Answering
Spoken question answering (SQA) is a challenging task that requires the machine to fully understand the complex spoken documents. Automatic speech recognition (ASR) plays a significant role in the development of QA systems. However, the recent work shows that ASR systems generate highly noisy transcripts, which critically limit the capability of machine comprehension on the SQA task. To address the issue, we present a novel distillation framework. Specifically, we devise a training strategy to perform knowledge distillation (KD) from spoken documents and written counterparts. Our work makes a step towards distilling knowledge from the language model as a supervision signal to lead to better student accuracy by reducing the misalignment between automatic and manual transcriptions. Experiments demonstrate that our approach outperforms several state-of-the-art language models on the Spoken-SQuAD dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Knowledge DistillationLanguage ModelingLanguage ModellingQuestion AnsweringReading Comprehensionspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Contextualized Attention-based Knowledge Transfer for Spoken Conversational Question Answering
Spoken conversational question answering (SCQA) requires machines to model complex dialogue flow given the speech utterances and text corpora. Different from traditional text question answering (QA) tasks, SCQA involves …
Audio Signal ProcessingConversational Question AnsweringKnowledge DistillationQuestion Answering+1Towards Data Distillation for End-to-end Spoken Conversational Question Answering
In spoken question answering, QA systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via hum…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Conversational Question AnsweringQuestion Answering+2End-to-end Spoken Conversational Question Answering: Task, Dataset and Model
In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via hu…
4kConversational Question AnsweringQuestion AnsweringSpoken Language Understanding+1I$^2$KD-SLU: An Intra-Inter Knowledge Distillation Framework for Zero-Shot Cross-Lingual Spoken Language Understanding
Spoken language understanding (SLU) typically includes two subtasks: intent detection and slot filling. Currently, it has achieved great success in high-resource languages, but it still remains challenging in low-resourc…
Intent DetectionKnowledge Distillationslot-fillingSlot Filling+1Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering
Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies. Towards these ends, we…
Knowledge GraphsQuestion AnsweringSpeech-to-TextSpoken Language Understanding+1