Hao Huang

Hao Jian Huang, Hakan T. Otal, M. Abdullah Canbaz

This paper presents the design and implementation of a Federated Learning (FL) testbed, focusing on its application in cybersecurity and evaluating its resilience against poisoning attacks. Federated Learning allows multiple clients to collaboratively train a global model while keeping their data decentralized, addressing critical needs for data privacy and security, particularly in sensitive fields like cybersecurity. Our testbed, built using Raspberry Pi and Nvidia Jetson hardware by running the Flower framework, facilitates experimentation with various FL frameworks, assessing their performance, scalability, and ease of integration. Through a case study on federated intrusion detection systems, the testbed's capabilities are shown in detecting anomalies and securing critical infrastructure without exposing sensitive network data. Comprehensive poisoning tests, targeting both model and data integrity, evaluate the system's robustness under adversarial conditions. The results show that while federated learning enhances data privacy and distributed learning, it remains vulnerable to poisoning attacks, which must be mitigated to ensure its reliability in real-world applications.

Saierdaer Yusuyin, Te Ma, Hao Huang et al.

Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across languages. However, a limitation is that a pronunciation lexicon is needed for such phoneme-based crosslingual speech recognition. In this study, we aim to eliminate the need for pronunciation lexicons and propose a latent variable model based method, with phonemes being treated as discrete latent variables. The new method consists of a speech-to-phoneme (S2P) model and a phoneme-to-grapheme (P2G) model, and a grapheme-to-phoneme (G2P) model is introduced as an auxiliary inference model. To jointly train the three models, we utilize the joint stochastic approximation (JSA) algorithm, which is a stochastic extension of the EM (expectation-maximization) algorithm and has demonstrated superior performance particularly in estimating discrete latent variable models. Based on the Whistle multilingual pre-trained S2P model, crosslingual experiments are conducted in Polish (130 h) and Indonesian (20 h). With only 10 minutes of phoneme supervision, the new method, JSA-SPG, achieves 5\% error rate reductions compared to the best crosslingual fine-tuning approach using subword or full phoneme supervision. Furthermore, it is found that in language domain adaptation (i.e., utilizing cross-domain text-only data), JSA-SPG outperforms the standard practice of language model fusion via the auxiliary support of the G2P model by 9% error rate reductions. To facilitate reproducibility and encourage further exploration in this field, we open-source the JSA-SPG training code and complete pipeline.

Te Ma, Min Bi, Saierdaer Yusuyin et al.

In automatic speech recognition (ASR), phoneme-based multilingual pre-training and crosslingual fine-tuning is attractive for its high data efficiency and competitive results compared to subword-based models. However, Weighted Finite State Transducer (WFST) based decoding is limited by its complex pipeline and inability to leverage large language models (LLMs). Therefore, we propose LLM-based phoneme-to-grapheme (LLM-P2G) decoding for phoneme-based ASR, consisting of speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G). A challenge is that there seems to have information loss in cascading S2P and P2G. To address this challenge, we propose two training strategies: data augmentation with noisy phonemes (DANP), and randomized top-$K$ marginalized (TKM) training and decoding. Our experimental results show that LLM-P2G outperforms WFST-based systems in crosslingual ASR for Polish and German, by relative WER reductions of 3.6% and 6.9% respectively.

Hao Huang, Yujie Lin, Siyu Chen et al.

Skeleton-based action recognition using GCNs has achieved remarkable performance, but recognizing ambiguous actions, such as "waving" and "saluting", remains a significant challenge. Existing methods typically rely on a serial combination of GCNs and TCNs, where spatial and temporal features are extracted independently, leading to an unbalanced spatial-temporal information, which hinders accurate action recognition. Moreover, existing methods for ambiguous actions often overemphasize local details, resulting in the loss of crucial global context, which further complicates the task of differentiating ambiguous actions. To address these challenges, we propose a lightweight plug-and-play module called SF-Head, inserted between GCN and TCN layers. SF-Head first conducts SSTE with a Feature Redundancy Loss (F-RL), ensuring a balanced interaction. It then performs AC-FA, with a Feature Consistency Loss (F-CL), which aligns the aggregated feature with their original spatial-temporal feature. Experimental results on NTU RGB+D 60, NTU RGB+D 120, NW-UCLA and PKU-MMD I datasets demonstrate significant improvements in distinguishing ambiguous actions.

Tingzhi Mao, Yerbolat Khassanov, Van Tung Pham et al.

In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance. The underrepresented words correspond to rare or out-of-vocabulary (OOV) words in the training data, and thereby can't be modeled reliably. We begin with graphemic lexicon which allows to drop the necessity of phonetic models in hybrid ASR. We study it under different settings and demonstrate its effectiveness in dealing with underrepresented NEs. Next, we study the impact of neural language model (LM) with letter-based features derived to handle infrequent words. After that, we attempt to enrich representations of underrepresented NEs in pretrained neural LM by borrowing the embedding representations of rich-represented words. This let us gain significant performance improvement on underrepresented NE recognition. Finally, we boost the likelihood scores of utterances containing NEs in the word lattices rescored by neural LMs and gain further performance improvement. The combination of the aforementioned approaches improves NE recognition by up to 42% relatively.

Hao Huang, Ying Hu, Haihua Xu

We propose an Encoder-Classifier framework to model the Mandarin tones using recurrent neural networks (RNN). In this framework, extracted frames of features for tone classification are fed in to the RNN and casted into a fixed dimensional vector (tone embedding) and then classified into tone types using a softmax layer along with other auxiliary inputs. We investigate various configurations that help to improve the model, including pooling, feature splicing and utilization of syllable-level tone embeddings. Besides, tone embeddings and durations of the contextual syllables are exploited to facilitate tone classification. Experimental results on Mandarin tone classification show the proposed network setups improve tone classification accuracy. The results indicate that the RNN encoder-classifier based tone model flexibly accommodates heterogeneous inputs (sequential and segmental) and hence has the advantages from both the sequential classification tone models and segmental classification tone models.