1 citations · 1 across the 8 of their papers we have counts for
9 papers
What Makes Codec Tokens Effective for Target Speaker Extraction? A Semantic-Acoustic Disentanglement Perspective
Wang Xiang, Bang Zeng, Ming Li
Target speaker extraction (TSE) aims to recover a target speaker's speech from a speech mixture using an enrollment utterance. Recent codec-based generative approaches formulate TS…
Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models
Bang Zeng, Beilong Tang, Wang Xiang +1
Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improvin…
Robust Audio-Visual Target Speaker Extraction with Emotion-Aware Multiple Enrollment Fusion
Zhan Jin, Bang Zeng, Peijun Yang +5
Audio-Visual Target Speaker Extraction (AVTSE) is crucial for cocktail party scenarios. Leveraging multiple cues --such as utterance-level speaker embeddings or steady face images,…
SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization
Beilong Tang, Xiaoxiao Miao, Xin Wang +1
Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode li…
LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models
Beilong Tang, Bang Zeng, Ming Li
We propose LauraTSE, an Auto-Regressive Decoder-Only Language Model for Target Speaker Extraction built upon the LauraGPT backbone. LauraTSE employs a small-scale auto-regressive d…
Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection
Bang Zeng, Ming Li
Determining 'who spoke what and when' remains challenging in real-world applications. In typical scenarios, Speaker Diarization (SD) is employed to address the problem of 'who spok…
TSELM: Target Speaker Extraction using Discrete Tokens and Language Models
Beilong Tang, Bang Zeng, Ming Li
We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input token…
A Dual-Path Framework with Frequency-and-Time Excited Network for Anomalous Sound Detection
Yucong Zhang, Juan Liu, Yao Tian +2
In contrast to human speech, machine-generated sounds of the same type often exhibit consistent frequency characteristics and discernible temporal periodicity. However, leveraging…
USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction
Bang Zeng, Ming Li
Target speaker extraction aims to separate the voice of a specific speaker from mixed speech. Traditionally, this process has relied on extracting a speaker embedding from a refere…