7 papers
Xiaomi-CocktailASR-1 Technical Report
Yiru Zhang, Hang Su, Lichun Fan +10
Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party prob…
Speech-to-See: End-to-End Speech-Driven Open-Set Object Detection
Wenhuan Lu, Xinyue Song, Wenjun Ke +3
Audio grounding, or speech-driven open-set object detection, aims to localize and identify objects directly from speech, enabling generalization beyond predefined categories. This…
Listening for "You": Enhancing Speech Image Retrieval via Target Speaker Extraction
Wenhao Yang, Jianguo Wei, Wenhuan Lu +2
Image retrieval using spoken language cues has emerged as a promising direction in multimodal perception, yet leveraging speech in multi-speaker scenarios remains challenging. We p…
You Only Speak Once to See
Wenhao Yang, Jianguo Wei, Wenhuan Lu +1
Grounding objects in images using visual cues is a well-established approach in computer vision, yet the potential of audio as a modality for object recognition and grounding remai…
Integrated Multi-Level Knowledge Distillation for Enhanced Speaker Verification
Wenhao Yang, Jianguo Wei, Wenhuan Lu +2
Knowledge distillation (KD) is widely used in audio tasks, such as speaker verification (SV), by transferring knowledge from a well-trained large model (the teacher) to a smaller,…
Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label
Wenhao Yang, Jianguo Wei, Wenhuan Lu +2
Domain gap often degrades the performance of speaker verification (SV) systems when the statistical distributions of training data and real-world test speech are mismatched. Channe…
Robust Channel Learning for Large-Scale Radio Speaker Verification
Wenhao Yang, Jianguo Wei, Wenhuan Lu +2
Recent research in speaker verification has increasingly focused on achieving robust and reliable recognition under challenging channel conditions and noisy environments. Identifyi…