End-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 …
contiguous text spans within the related speech transcripts. However, the most natural way …
Constructing better prototype generators with 3D CNNs for few-shot text classification
Prototypical network is a key algorithm to solve few-shot problems. Previous prototypical
network based methods average sentence embeddings of the same class to obtain …
network based methods average sentence embeddings of the same class to obtain …
Megan: memory enhanced graph attention network for space-time video super-resolution
Abstract Space-time video super-resolution (STVSR) aims to construct a high space-time
resolution video sequence from the corresponding low-frame-rate, low-resolution video …
resolution video sequence from the corresponding low-frame-rate, low-resolution video …
MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-Experts
X Cheng, Z Zhu, X Zhuang, Z Chen… - Findings of the …, 2024 - aclanthology.org
As a crucial task in the task-oriented dialogue systems, spoken language understanding
(SLU) has garnered increasing attention. However, errors from automatic speech …
(SLU) has garnered increasing attention. However, errors from automatic speech …
Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding
X Cheng, Z Zhu, B Yang, X Zhuang, H Li… - Findings of the …, 2024 - aclanthology.org
Owing to the scarcity of labeled training data, Spoken Language Understanding (SLU) is still
a challenging task in low-resource languages. Therefore, zero-shot cross-lingual SLU …
a challenging task in low-resource languages. Therefore, zero-shot cross-lingual SLU …
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification
Few-shot Intent Classification (FSIC) is one of the key challenges in modular task-oriented
dialog systems. While advanced FSIC methods are similar in using pretrained language …
dialog systems. While advanced FSIC methods are similar in using pretrained language …
Calibrate and refine! a novel and agile framework for asr-error robust intent detection
The past ten years have witnessed the rapid development of text-based intent detection,
whose benchmark performances have already been taken to a remarkable level by deep …
whose benchmark performances have already been taken to a remarkable level by deep …
Exploring the limits of natural language inference based setup for few-shot intent detection
A Kumar, V Malik, J Vepa - arXiv preprint arXiv:2112.07434, 2021 - arxiv.org
Intent Detection is one of the core tasks of dialog systems. Few-shot Intent Detection is
challenging due to limited number of annotated utterances for novel classes. Generalized …
challenging due to limited number of annotated utterances for novel classes. Generalized …
Low-resource accent classification in geographically-proximate settings: A forensic and sociophonetics perspective
Accented speech recognition and accent classification are relatively under-explored
research areas in speech technology. Recently, deep learning-based methods and …
research areas in speech technology. Recently, deep learning-based methods and …
基于小样本学习的口语理解方法综述.
刘纳， 郑国风， 徐贞顺， 林令德… - Journal of Zhengzhou …, 2024 - search.ebscohost.com
小样本口语理解是目前对话式人工智能亟待解决的问题之一. 结合国内外最新研究现状,
系统地梳理了口语理解任务的相关文献. 简要介绍了在非小样本场景中口语理解任务建模的经典 …
系统地梳理了口语理解任务的相关文献. 简要介绍了在非小样本场景中口语理解任务建模的经典 …