arXiv subjects

Jinghao Chen

Publications and source records attributed to Jinghao Chen.

5 recordsLinked to original sources

arXiv2026

Mandarin Humorous Homophone Recognition and Disambiguation in Automatic Speech Recognition

Mandarin homophones remain a key challenge to improving automatic speech recognition (ASR) accuracy due to the amount of potential homophones. Mandarin speakers use this feature casually to convey emotions such as humour. Recent homophone-aware ASR studies have improved recognition accuracy, but intentional homophone twists in speech remain underexplored. In this paper, we identify patterns of homophone-based rhetorical wordplay in Mandarin, referred to as HumourPhone, and propose an ASR Adapter for homophone and HumourPhone recovery. Experimental results show that the proposed approach improves the recall of recognising HumourPhone by over 5\% and achieves a 4.35\% drop in target-span character error rate for homophone correction compared to baseline. These results highlight the need for homophone-aware modelling of lexical ambiguity and rhetorical wordplay in Mandarin speech recognition.

eess.AS↗

arXiv2026

Using Phonological-Level Wav2Vec2 for Mandarin Automatic Mispronunciation Detection and Diagnosis

Automatic mispronunciation detection and diagnosis (MDD) plays a crucial role in L2 Mandarin pronunciation learning. While end-to-end (E2E) based MDD methods have substantially improved phoneme-level detection accuracy, diagnostic feedback remains limited, as segmental and tonal errors are not explicitly separated. In this paper, we propose a phonological feature-based MDD framework that models both segmental and tonal attributes within a unified Wav2Vec2 CTC architecture. Experimental results show that the proposed method reduces the False Acceptance Rate (FAR) by 10.1% and the Diagnostic Error Rate (DER) by 23.6% compared with the phoneme-only baseline system. By decomposing phonemes into low-level phonological components, the proposed approach enables more detailed and interpretable diagnostic feedback for L2 learners.

eess.AS↗

arXiv2025

VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding

Generative auto-bidding has demonstrated strong performance in online advertising, yet it often suffers from data scarcity in small-scale settings with limited advertiser participation. While cross-task data sharing is a natural remedy to mitigate this issue, naive approaches often introduce gradient bias due to distribution shifts across different tasks, and existing methods are not readily applicable to generative auto-bidding. In this paper, we propose Validation-Aligned Optimization (VAO), a principled data-sharing method that adaptively reweights cross-task data contributions based on validation performance feedback. Notably, VAO aligns training dynamics to prioritize updates that improve generalization on the target task, effectively leveraging auxiliary data and mitigating gradient bias. Building on VAO, we introduce a unified generative autobidding framework that generalizes across multiple tasks using a single model and all available task data. Extensive experiments on standard auto-bidding benchmarks validate the effectiveness of our approach.

cs.LG↗

arXiv2025

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search

Auto-bidding is a critical tool for advertisers to improve advertising performance. Recent progress has demonstrated that AI-Generated Bidding (AIGB), which learns a conditional generative planner from offline data, achieves superior performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods. However, existing AIGB methods still face a performance bottleneck due to their inherent inability to explore beyond the static dataset with feedback. To address this, we propose \textbf{AIGB-Pearl} (\emph{\textbf{P}lanning with \textbf{E}valu\textbf{A}tor via \textbf{RL}}), a novel method that integrates generative planning and policy optimization. The core of AIGB-Pearl lies in constructing a trajectory evaluator to assess the quality of generated scores and designing a provably sound KL-Lipschitz-constrained score-maximization scheme to ensure safe and efficient exploration beyond the offline dataset. A practical algorithm that incorporates the synchronous coupling technique is further developed to ensure the model regularity required by the proposed scheme. Extensive experiments on both simulated and real-world advertising systems demonstrate the state-of-the-art performance of our approach.

cs.LG↗

arXiv2016

Ultrafast inhomogeneous magnetization dynamics analyzed by interface-sensitive nonlinear magneto-optics

We analyze laser-induced ultrafast, spatially inhomogeneous magnetization dynamics of epitaxial Co/Cu(001) films in a 0.4-10 nm thickness range with time-resolved magnetization-induced second harmonic generation, which probes femtosecond spin dynamics at the vacuum/Co and Co/Cu interfaces. The interference of these two contributions makes the overall signal particularly sensitive to differences in the transient magnetization redistribution between the two interfaces, i.e. ultrafast magnetization profiles in the ferromagnetic film. We find in films of up to 3 nm thickness a stronger demagnetization at the surface, because the film thickness is smaller than the effective mean free path of the spin current mediating the demagnetization, i.e. the difference between the mean free paths of the majority and minority carriers. For film thicknesses larger than 3 nm, the magnetization profile reverses, since majority spins can escape into the conducting substrate only from the interface-near region.

cond-mat.mtrl-sci↗