Related papers: I$^2$KD-SLU: An Intra-Inter Knowledge Distillation…
Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…
This paper introduces the system submitted by the DKU-SMIIP team for the Auto-KWS 2021 Challenge. Our implementation consists of a two-stage keyword spotting system based on query-by-example spoken term detection and a speaker verification…
Knowledge distillation (KD) is a highly promising method for mitigating the computational problems of pre-trained language models (PLMs). Among various KD approaches, Intermediate Layer Distillation (ILD) has been a de facto standard KD…
Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text…
This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers…
The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus achieving a desirable knowledge transfer to unseen classes. Prior works either…
Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts…
Intelligent virtual assistants are currently designed to perform tasks or services explicitly mentioned by users, so multiple related domains or tasks need to be performed one by one through a long conversation with many explicit intents.…
Semi-supervised learning (SSL) has emerged as a practical solution for addressing data scarcity challenges by leveraging unlabeled data. Recently, vision-language models (VLMs), pre-trained on massive image-text pairs, have demonstrated…
For natural language understanding (NLU) technology to be maximally useful, both practically and as a scientific object of study, it must be general: it must be able to process language in a way that is not exclusively tailored to any one…
Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request. We propose a scalable and automatic…
Natural Language Understanding (NLU) is a core component of dialog systems. It typically involves two tasks - intent classification (IC) and slot labeling (SL), which are then followed by a dialogue management (DM) component. Such NLU…
Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In particular, there are not…
A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…
Human-computer interaction (HCI) is significantly impacted by delayed responses from a spoken dialogue system. Hence, end-to-end (e2e) spoken language understanding (SLU) solutions have recently been proposed to decrease latency. Such…
Intelligent systems designed for play-based interactions should be contextually aware of the users and their surroundings. Spoken Dialogue Systems (SDS) are critical for these interactive agents to carry out effective goal-oriented…
Intent classification is a task in spoken language understanding. An intent classification system is usually implemented as a pipeline process, with a speech recognition module followed by text processing that classifies the intents. There…
Much recent work on Spoken Language Understanding (SLU) falls short in at least one of three ways: models were trained on oracle text input and neglected the Automatics Speech Recognition (ASR) outputs, models were trained to predict only…
Recurrent neural network (RNN) based joint intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems. However, these models suffer from poor…
Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…