arXiv subjects

Xianglong Wang

Publications and source records attributed to Xianglong Wang.

3 recordsLinked to original sources

arXiv2026

AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition

On-device speech emotion recognition (SER) is critical for real-time applications, yet large self-supervised models that excel at SER are too costly for edge devices. Multi-teacher knowledge distillation can compress them into a lightweight student, but two challenges remain: teacher reliability varies across batches, and logit-level distillation ignores inter-sample relational structure. We propose Adaptive Multi-teacher Relational Distillation (AMRD) to address both. A one-class SVM on each teacher's logit similarity matrix assigns per-batch weights favoring more coherent teachers. A relational distillation loss aligns teacher and student similarity matrices, capturing structure that logit matching misses. On IEMOCAP and CREMA-D datasets across four student architectures, AMRD outperforms single-teacher distillation baselines in most settings, and ablations confirm both components yield complementary gains.

cs.LG↗

arXiv2024

OpenAirLink: Reproducible Wireless Channel Emulation using Software Defined Radios

This paper presents OpenAirLink(OAL), an open-source channel emulator for reproducible testing of wireless scenarios. OAL is implemented on off-the-shelf software-defined radios (SDR) and presents a smaller-scale alternative to expensive commercially available channel emulators. Path loss and propagation delay are the fundamental aspects of emulating a wireless channel. OAL provides a simple method to change these aspects in real-time. The emulator is implemented using a finite impulse response (FIR) filter. The FIR filter is written in Verilog and flashed on the SDRs Field Programmable Gate Array (FPGA). Most processing transpires on the FPGA, so OAL does not require high-performance computing hardware and SDRs. We validate the performance of OAL and demonstrate the utility of such a channel emulation tool using two examples. We believe that open-source channel emulators such as OAL can make reproducible wireless experiments accessible to many researchers in the scientific community.

cs.NI↗

arXiv2023

Ordered and Binary Speaker Embedding

Modern speaker recognition systems represent utterances by embedding vectors. Conventional embedding vectors are dense and non-structural. In this paper, we propose an ordered binary embedding approach that sorts the dimensions of the embedding vector via a nested dropout and converts the sorted vectors to binary codes via Bernoulli sampling. The resultant ordered binary codes offer some important merits such as hierarchical clustering, reduced memory usage, and fast retrieval. These merits were empirically verified by comprehensive experiments on a speaker identification task with the VoxCeleb and CN-Celeb datasets.

cs.SD↗