Related papers: Reading Between the Lines: The One-Sided Conversat…
The conversational machine reading comprehension (CMRC) task aims to answer questions in conversations, which has been a hot research topic in recent years because of its wide applications. However, existing CMRC benchmarks in which each…
Personalized conversation models (PCMs) generate responses according to speaker preferences. Existing personalized conversation tasks typically require models to extract speaker preferences from user descriptions or their conversation…
Conversational Question Answering (ConvQA) models aim at answering a question with its relevant paragraph and previous question-answer pairs that occurred during conversation multiple times. To apply such models to a real-world scenario,…
Large language models (LLMs) excel on static benchmarks, but their performance across multi-turn conversations, which better reflect real-world usage, remains understudied. Addressing this gap is critical in high-stakes settings like…
It is popular lately to train large language models to be used as chat assistants, but in the conversation between the user and the chat assistant, there are prompts, require multi-turns between the chat assistant and the user. However,…
ASR models often suffer from a long-form deletion problem where the model predicts sequential blanks instead of words when transcribing a lengthy audio (in the order of minutes or hours). From the perspective of a user or downstream system…
As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two…
Structured sentences are important expressions in human writings and dialogues. Previous works on neural text generation fused semantic and structural information by encoding the entire sentence into a mixed hidden representation. However,…
Neural dialogue models have been widely adopted in various chatbot applications because of their good performance in simulating and generalizing human conversations. However, there exists a dark side of these models -- due to the…
A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn…
It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR).…
Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans. Video question answering is a specific scenario of such AI-human…
Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers. At the core of our method is a deep network, in the waveform domain,…
While large language models (LLMs) have shown remarkable capabilities to generate coherent text, they suffer from the issue of hallucinations -- factually inaccurate statements. Among numerous approaches to tackle hallucinations, especially…
Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found…
A system that could reliably identify and sum up the most important points of a conversation would be valuable in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls. Recent…
In neural dialogue modeling, a neural network is trained to predict the next utterance, and at inference time, an approximate decoding algorithm is used to generate next utterances given previous ones. While this autoregressive framework…
Recently, large language models (LLMs), such as GPT-4, stand out remarkable conversational abilities, enabling them to engage in dynamic and contextually relevant dialogues across a wide range of topics. However, given a long conversation,…
We present a speaker-aware approach for simulating multi-speaker conversations that captures temporal consistency and realistic turn-taking dynamics. Prior work typically models aggregate conversational statistics under an independence…
Turn-taking is a fundamental mechanism in human communication that ensures smooth and coherent verbal interactions. Recent advances in Large Language Models (LLMs) have motivated their use in improving the turn-taking capabilities of Spoken…