Jingru Lin

Interpolating Speaker Identities in Embedding Space for Data Expansion

Tianchi Liu, Ruijie Tao, Qiongqiong Wang, Yidi Jiang et autres

The success of deep learning-based speaker verification systems is largely attributed to access to large-scale and diverse speaker identity data. However, collecting data from more identities is expensive, challenging, and often limited by privacy concerns. To address this limitation, we propose INSIDE …

sg, cn (code pays fourni par la source)

Reinforcement Learning Foundations for Deep Research Systems: A Survey

Wei Li, Zhi Chen, Jingru Lin, Wei Han et autres

Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and Executors. In practice, training entire stacks end-to-end remains …

Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction

Jingru Lin, Meng Ge, Yu Jiang, Xiaobao Wang et autres

A high-quality enrollment speech is crucial to target speaker extraction (TSE), since it provides essential cues for identifying the target speaker in the mixture. However, real applications usually only permit a short enrollment speech, e.g. a wakeup word for a mobile device, …

cn, sg (code pays fourni par la source)

SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech

Jingru Lin, Meng Ge, Junyi Ao, Liqun Deng et autres

It was shown that pre-trained models with self-supervised learning (SSL) techniques are effective in various downstream speech tasks.However, most such models are trained on singlespeaker speech data, limiting their effectiveness in mixture speech.This motivates us to explore pre-training on mixture speech.This work …

sg, cn, se (code pays fourni par la source)

SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech

Jingru Lin, Meng Ge, Junyi Ao, Liqun Deng et autres

It was shown that pre-trained models with self-supervised learning (SSL) techniques are effective in various downstream speech tasks. However, most such models are trained on single-speaker speech data, limiting their effectiveness in mixture speech. This motivates us to explore pre-training on mixture …

Selective HuBERT: Self-Supervised Pre-Training for Target Speaker in Clean and Mixture Speech

Jingru Lin, Meng Ge, Wupeng Wang, Haizhou Li et autres

Self-supervised pre-trained speech models were shown effective for various downstream speech processing tasks. Since they are mainly pre-trained to map input speech to pseudo-labels, the resulting representations are only effective for the type of pre-train data used, either clean or mixture speech. …

sg, cn (code pays fourni par la source)

Pilots’ Fatigue Status Recognition Using Deep Contractive Autoencoder Network

Edmond Q. Wu, Xiuhua Peng, Caizhi Z. Zhang, Jingru Lin et autres

The evaluation of pilots' fatigue status is of substantial significance in aviation safety, which faces two major issues. They are how to get the fatigue status feature representation and how to identify the fatigue behavior status of pilots via electroencephalogram (EEG) signals. …

cn (code pays fourni par la source)