相关论文: EchoChain: A Full-Duplex Benchmark for State-Updat…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
We present a real-time front-end for voice-based conversational AI to enable natural turn-taking in two-speaker scenarios by combining primary speaker segmentation with hierarchical End-of-Turn (EOT) detection. To operate robustly in…
Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatch between speech tokens (25Hz) and text tokens (~3Hz)…
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood. We propose controllable counterfactuals…
Large Audio-Language Models (LALMs), such as GPT-4o, have recently unlocked audio dialogue capabilities, enabling direct spoken exchanges with humans. The potential of LALMs broadens their applicability across a wide range of practical…
Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual…
Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from interacting during the user's turn and can lead to high…
Full-duplex voice interaction allows users and agents to speak simultaneously with controllable barge-in, enabling lifelike assistants and customer service. Existing solutions are either end-to-end, difficult to design and hard to control,…
Post-exercise speech contains rich physiological and linguistic cues, often marked by semantic pauses, breathing pauses, and combined breathing-semantic pauses. Detecting these events enables assessment of recovery rate, lung function, and…
In spoken conversations, spontaneous behaviors like filled pause and prolongations always happen. Conversational partner tends to align features of their speech with their interlocutor which is known as entrainment. To produce human-like…
Partial deepfake speech detection requires identifying manipulated regions that may occur within short temporal portions of an otherwise bona fide utterance, making the task particularly challenging for conventional utterance-level…
During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental…
A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain…
Open-vocabulary state tracking is a more practical version of state tracking that aims to track state changes of entities throughout a process without restricting the state space and entity space. OpenPI is to date the only dataset…
Recent advances in spoken dialogue systems have brought increased attention to human-like full-duplex voice interactions. However, our comprehensive review of this field reveals several challenges, including the difficulty in obtaining…
Recent reports suggest that LLMs can handle increasingly long contexts. However, many existing benchmarks for context understanding embed substantial query-irrelevant content, which shifts evaluation toward retrieving relevant snippets…
Identifying the root cause of a bug remains difficult for many developers because bug reports often lack a bug reproducing test case that reliably triggers the failure. Manually writing such test cases is time-consuming and requires…
A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continually training a model often leads to a well-known…
Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the…
The task of dialogue generation aims to automatically provide responses given previous utterances. Tracking dialogue states is an important ingredient in dialogue generation for estimating users' intention. However, the \emph{expensive…