Related papers: An Adversarial Learning based Multi-Step Spoken La…
Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers are still a tedious process with challenges such as costly data annotation and privacy risks. In this paper, we suggest an alternative,…
Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the…
Large language model-based agents are increasingly applied in the recommendation field due to their extensive knowledge and strong planning capabilities. While prior research has primarily focused on enhancing either the recommendation…
We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisition-oriented dialogue system…
This paper presents our latest effort on improving Code-switching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a…
Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users…
With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most monaural speech enhancement (SE) models introduce processing…
Many approaches to Natural Language Processing (NLP) tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, human language is inherently…
Conversational AI systems combine AI-based solutions with the flexibility of conversational interfaces. However, most existing testing solutions do not straightforwardly adapt to the characteristics of conversational interaction or to the…
Automatic evaluation is beneficial for open-domain dialog system development. However, standard word-overlap metrics (BLEU, ROUGE) do not correlate well with human judgements of open-domain dialog systems. In this work we propose to use the…
Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language…
Voice-controlled dialog systems have become immensely popular due to their ability to perform a wide range of actions in response to diverse user queries. These agents possess a predefined set of skills or intents to fulfill specific user…
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response…
Conversational recommender systems (CRSs) are improving rapidly, according to the standard recommendation accuracy metrics. However, it is essential to make sure that these systems are robust in interacting with users including regular and…
Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…
Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural…
As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluations fail to…
Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks. In the 1990's it was discovered, that conversational speech between two humans…
Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and…
User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total…