Related papers: Controllable User Dialogue Act Augmentation for Di…
Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging…
Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To…
Most of the current speech data augmentation methods operate on either the raw waveform or the amplitude spectrum of speech. In this paper, we propose a novel speech data augmentation method called PhasePerturbation that operates…
Popular dialog datasets such as MultiWOZ are created by providing crowd workers an instruction, expressed in natural language, that describes the task to be accomplished. Crowd workers play the role of a user and an agent to generate…
Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems. Since dialogue management requires to have access to not only…
End-to-end Speech Translation is hindered by a lack of available data resources. While most of them are based on documents, a sentence-level version is available, which is however single and static, potentially impeding the usefulness of…
A Dialogue State Tracker is a key component in dialogue systems which estimates the beliefs of possible user goals at each dialogue turn. Deep learning approaches using recurrent neural networks have shown state-of-the-art performance for…
The construction of open-domain dialogue systems requires high-quality dialogue datasets. The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics. However, collecting…
Task-oriented dialogue systems are essential for applications ranging from customer service to personal assistants and are widely used across various industries. However, developing effective multi-domain systems remains a significant…
Data augmentation (DA) is ubiquitously used in training of Automatic Speech Recognition (ASR) models. DA offers increased data variability, robustness and generalization against different acoustic distortions. Recently, personalization of…
In this paper, we introduce Dependency Dialogue Acts (DDA), a novel framework for capturing the structure of speaker-intentions in multi-party dialogues. DDA combines and adapts features from existing dialogue annotation frameworks, and…
Recently, reinforcement learning (RL) has been applied to task-oriented dialogue systems by using latent actions to solve shortcomings of supervised learning (SL). In this paper, we propose a multi-domain task-oriented dialogue system,…
The medical dialogue system is a promising application that can provide great convenience for patients. The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure…
User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that…
Much recent progress in task-oriented dialogue (ToD) systems has been driven by available annotation data across multiple domains for training. Over the last few years, there has been a move towards data curation for multilingual ToD…
Task-oriented dialogues often require agents to enact complex, multi-step procedures in order to meet user requests. While large language models have found success automating these dialogues in constrained environments, their widespread…
Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role…
Large-scale Wizard-Of-Oz dialogue datasets have enabled the training of deep learning-based dialogue systems. While they are successful as benchmark datasets, they lack certain types of utterances, which would make them more realistic. In…
In a human-machine dialog scenario, deciding the appropriate time for the machine to take the turn is an open research problem. In contrast, humans engaged in conversations are able to timely decide when to interrupt the speaker for…
Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations. Recent state-of-the-art DST implementations rely on schemata of diverse services to improve model robustness and handle…