相关论文: Contrastive Speaker-Aware Learning for Multi-party…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Chatbots or conversational agents (CAs) are increasingly used to improve access to digital psychotherapy. Many current systems rely on rigid, rule-based designs, heavily dependent on expert-crafted dialogue scripts for guiding therapeutic…

Sign Language Translation (SLT) bridges the communication gap between deaf people and hearing people, where dialogue provides crucial contextual cues to aid in translation. Building on this foundational concept, this paper proposes…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in end-to-end speaker diarization and recognition. However, their speaker discriminability remains limited due to the scarcity of large-scale conversational data…

Large Language Models (\textbf{LLMs}), e.g. ChatGPT, have been widely adopted in real-world dialogue applications. However, LLMs' robustness, especially in handling long complex dialogue sessions, including frequent motivation transfer,…

Although large language models(LLMs) show amazing capabilities, among various exciting applications discovered for LLMs fall short in other low-resource languages. Besides, most existing methods depend on large-scale dialogue corpora and…

Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language models (SLMs), which use speech as input, are emerging as a…

Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin…

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive…

Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the self-augmented dialog samples as positive samples and treats…

Empathetic dialogue is an indispensable part of building harmonious social relationships and contributes to the development of a helpful AI. Previous approaches are mainly based on fine small-scale language models. With the advent of…

Multi-session persona-based dialogue generation presents challenges in maintaining long-term consistency and generating diverse, personalized responses. While large language models (LLMs) excel in single-session dialogues, they struggle to…

Deriving multimodal representations of audio and lexical inputs is a central problem in Natural Language Understanding (NLU). In this paper, we present Contrastive Aligned Audio-Language Multirate and Multimodal Representations (CALM), an…

Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works well for tasks that only require forward…

This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion…

Multilingual speech emotion recognition aims to estimate a speaker's emotional state using a contactless method across different languages. However, variability in voice characteristics and linguistic diversity poses significant challenges…

Auditory attention and selective phase-locking are central to human speech understanding in complex acoustic scenes and cocktail party settings, yet these capabilities in multilingual subjects remain poorly understood. While machine…

Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of…

Recently, data-driven task-oriented dialogue systems have achieved promising performance in English. However, developing dialogue systems that support low-resource languages remains a long-standing challenge due to the absence of…