Related papers: MMW: Side Talk Rejection Multi-Microphone Whisper …
State-of-the-art vocal separation models like Mel-Band-Roformer rely on full temporal self-attention mechanisms, where each temporal frame interacts with every other frames. This incurs heavy computational costs that scales quadratically…
Multichannel convolutive blind speech source separation refers to the problem of separating different speech sources from the observed multichannel mixtures without much a priori information about the mixing system. Multichannel nonnegative…
In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired…
Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and…
Weakly supervised semantic segmentation (WSSS) models relying on class activation maps (CAMs) have achieved desirable performance comparing to the non-CAMs-based counterparts. However, to guarantee WSSS task feasible, we need to generate…
The performance of millimeter-wave (mmWave) and sub-terahertz (sub-THz) communication systems is significantly impaired by sensitivity to sudden blockages. In this work, we employ machine learning (ML) and our physics-based simulation tool…
Dialogue state tracking models play an important role in a task-oriented dialogue system. However, most of them model the slot types conditionally independently given the input. We discover that it may cause the model to be confused by slot…
User-defined keyword spotting (KWS) without resorting to domain-specific pre-labeled training data is of fundamental importance in building adaptable and personalized voice interfaces. However, such systems are still faced with arduous…
Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…
This research proposes the interaction loop model "ASR-LLMs-Smart Glasses", which model combines automatic speech recognition, large language model and smart glasses to facilitate seamless human-computer interaction. And the methodology of…
Millimeter Wave (mmWave) band provides a large spectrum to meet the high-demand capacity by the 5th generation (5G) wireless networks. However, to fully exploit the available spectrum, obstacles such as high path loss, channel sparsity, and…
Speech enhancement and separation have been a long-standing problem, especially with the recent advances using a single microphone. Although microphones perform well in constrained settings, their performance for speech separation decreases…
Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…
Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…
This paper introduces the system submitted by the DKU-SMIIP team for the Auto-KWS 2021 Challenge. Our implementation consists of a two-stage keyword spotting system based on query-by-example spoken term detection and a speaker verification…
This paper describes a system that gives a mobile robot the ability to perform automatic speech recognition with simultaneous speakers. A microphone array is used along with a real-time implementation of Geometric Source Separation and a…
Speech enhancement performance degrades significantly in noisy environments, limiting the deployment of speech-controlled technologies in industrial settings, such as manufacturing plants. Existing speech enhancement solutions primarly rely…
The multichannel Wiener filter (MWF) and its variations have been extensively applied to binaural hearing aids. However, its major drawback is the distortion of the binaural cues of the residual noise, changing the original acoustic…
Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…
Having knowledge on the room acoustic properties, e.g., the location of acoustic reflectors, allows to better reproduce the sound field as intended. Current state-of-the-art methods for room boundary detection using microphone measurements…