Related papers: FlexDuo: A Pluggable System for Enabling Full-Dupl…

While Large Language Models (LLMs) provide semantic flexibility for robotic task planning, their susceptibility to hallucination and logical inconsistency limits their reliability in long-horizon domains. To bridge the gap between…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their…

The Fluid Antenna System (FAS), which enables flexible Multiple-Input Multiple-Output (MIMO) communications, introduces new spatial degrees of freedom for next-generation wireless networks. Unlike traditional MIMO, FAS involves joint port…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

Robust task-oriented spoken dialogue agents require exposure to the full diversity of how people interact through speech. Building spoken user simulators that address this requires large-scale spoken task-oriented dialogue (TOD) data…

We consider a dynamic time division duplex (DTDD) enabled cell-free massive multiple-input multiple-output (CF-mMIMO) system, where each half-duplex (HD) access point (AP) is scheduled to operate in the uplink (UL) or downlink (DL) mode…

The goal of dialogue state tracking (DST) is to predict the current dialogue state given all previous dialogue contexts. Existing approaches generally predict the dialogue state at every turn from scratch. However, the overwhelming majority…

Instruction-tuned language models increasingly rely on large multi-turn dialogue corpora, but these datasets are often noisy and structurally inconsistent, with topic drift, repetitive chitchat, and mismatched answer formats across turns.…

The traditional vocoders have the advantages of high synthesis efficiency, strong interpretability, and speech editability, while the neural vocoders have the advantage of high synthesis quality. To combine the advantages of two vocoders,…

Dialogue state tracking (DST) is a key component of task-oriented dialogue systems. DST estimates the user's goal at each user turn given the interaction until then. State of the art approaches for state tracking rely on deep learning…

Modules in all existing speech separation networks can be categorized into single-input-multi-output (SIMO) modules and single-input-single-output (SISO) modules. SIMO modules generate more outputs than input, and SISO modules keep the…

We introduce Moshi, a speech-text foundation model and full-duplex spoken dialogue framework. Current systems for spoken dialogue rely on pipelines of independent components, namely voice activity detection, speech recognition, textual…

The capacity for highly complex, evidence-based, and strategically adaptive persuasion remains a formidable great challenge for artificial intelligence. Previous work, like IBM Project Debater, focused on generating persuasive speeches in…

Echo and noise suppression is an integral part of a full-duplex communication system. Many recent acoustic echo cancellation (AEC) systems rely on a separate adaptive filtering module for linear echo suppression and a neural module for…

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…

Simultaneous speech-to-speech translation (SimulS2S) is essential for real-time multilingual communication, with increasing integration into meeting and streaming platforms. Despite this, SimulS2S remains underexplored in research, where…

This paper considers the implementation and application possibilities of a compact full duplex multiple-input multiple-output (MIMO) architecture where direct communication exists between users, e.g., device-to-device (D2D) and cellular…

Although in cellular networks full-duplex and dynamic time-division duplexing promise increased spectrum efficiency, their potential is so far challenged by increased interference. While previous studies have shown that self-interference…

This paper considers a cellular system with a full-duplex base station and half-duplex users. The base station can activate one user in uplink or downlink (half-duplex mode), or two different users one in each direction simultaneously…