Related papers: Thinking-while-speaking: A Controlled, Interleaved…

Stylistic response generation is crucial for building an engaging dialogue system for industrial use. While it has attracted much research interest, existing methods often generate stylistic responses at the cost of the content quality…

Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conversations lengthen, essential information becomes sparse and…

Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmented Generation…

When humans speak, gestures help convey communicative intentions, such as adding emphasis or describing concepts. However, current co-speech gesture generation methods rely solely on superficial linguistic cues (e.g. speech audio or text…

Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…

Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing emotion intensity controllable TTS. Most existing TTS models achieve emotion intensity control by…

This paper introduces StyleSpeech, a novel Text-to-Speech~(TTS) system that enhances the naturalness and accuracy of synthesized speech. Building upon existing TTS technologies, StyleSpeech incorporates a unique Style Decorator structure…

Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-correction. While RL…

Counterspeech, defined as a response to mitigate online hate speech, is increasingly used as a non-censorial solution. Addressing hate speech effectively involves dispelling the stereotypes, prejudices, and biases often subtly implied in…

Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model:…

This paper presents a unified spoken language model for emotional intelligence, enhanced by a novel data construction strategy termed Injected Emotional-Attribution Thinking (IEAT). IEAT incorporates user emotional states and their…

While generative Text-to-Speech (TTS) systems leverage vast ``in-the-wild" data to achieve remarkable success, speech-to-speech processing tasks like enhancement face data limitations, which lead data-hungry generative approaches to distort…

While prompt-based text-to-speech (TTS) models enable natural language-driven speaking style control, they often provide limited fine-grained control and apply a single global style across an utterance. This restricts practical use cases…

In recent years, prompting has quickly become one of the standard ways of steering the outputs of generative machine learning models, due to its intuitive use of natural language. In this work, we propose a system conditioned on embeddings…

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and…

Recall the classical text generation works, the generation framework can be briefly divided into two phases: \textbf{idea reasoning} and \textbf{surface realization}. The target of idea reasoning is to figure out the main idea which will be…

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy…

We study reasoning tasks through a framework that integrates auto-regressive (AR) and non-autoregressive (NAR) language models. AR models, which generate text sequentially, excel at producing coherent outputs but often suffer from slow…

The emergence of generative AI has accelerated the development of conversational tutoring systems that interact with students through natural language dialogue. Unlike prior intelligent tutoring systems (ITS), which largely function as…

Recent Large Reasoning Language Models (LRLMs) employ long chain-of-thought reasoning with complex reflection behaviors, typically signaled by specific trigger words (e.g., "Wait" and "Alternatively") to enhance performance. However, these…