Cong Zhang

Wenhui Huang, Cong Zhang, Jingda Wu et al.

Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic exploration approaches either explore new actions heuristically regardless of Q-values or inevitably introduce bias into the learning process to couple the sampling with Q-values. In this paper, we propose a novel preference-guided $ε$-greedy exploration algorithm that can efficiently learn the action distribution in line with the landscape of Q-values for DQN without introducing additional bias. Specifically, we design a dual architecture consisting of two branches, one of which is a copy of DQN, namely the Q-branch. The other branch, which we call the preference branch, learns the action preference that the DQN implicit follows. We theoretically prove that the policy improvement theorem holds for the preference-guided $ε$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values. Consequently, preference-guided $ε$-greedy exploration motivates the DQN agent to take diverse actions, i.e., actions with larger Q-values can be sampled more frequently whereas actions with smaller Q-values still have a chance to be explored, thus encouraging the exploration. We assess the proposed method with four well-known DQN variants in nine different environments. Extensive results confirm the superiority of our proposed method in terms of performance and convergence speed. Index Terms- Preference-guided exploration, stochastic policy, data efficiency, deep reinforcement learning, deep Q-learning.

Jian Zhu, Zuoyu Tian, Yadong Liu et al.

Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic representations for spoken utterances. Through converting speech signals into hidden units generated from acoustic unit discovery, we propose WavEmbed, a multimodal sequential autoencoder that predicts hidden units from a dense representation of speech. Secondly, we also propose S-HuBERT to induce meaning through knowledge distillation, in which a sentence embedding model is first trained on hidden units and passes its knowledge to a speech encoder through contrastive learning. The best performing model achieves a moderate correlation (0.5~0.6) with human judgments, without relying on any labels or transcriptions. Furthermore, these models can also be easily extended to leverage textual transcriptions of speech to learn much better speech embeddings that are strongly correlated with human annotations. Our proposed methods are applicable to the development of purely data-driven systems for speech mining, indexing and search.

Jian Zhu, Cong Zhang, David Jurgens

The task of phone-to-audio alignment has many applications in speech research. Here we introduce two Wav2Vec2-based models for both text-dependent and text-independent phone-to-audio alignment. The proposed Wav2Vec2-FS, a semi-supervised model, directly learns phone-to-audio alignment through contrastive learning and a forward sum loss, and can be coupled with a pretrained phone recognizer to achieve text-independent alignment. The other model, Wav2Vec2-FC, is a frame classification model trained on forced aligned labels that can both perform forced alignment and text-independent segmentation. Evaluation results suggest that both proposed methods, even when transcriptions are not available, generate highly close results to existing forced alignment tools. Our work presents a neural pipeline of fully automated phone-to-audio alignment. Code and pretrained models are available at https://github.com/lingjzhu/charsiu.

Esteban Fernández Morales, Cong Zhang, Guanghua Xiao et al.

With the advanced imaging technology, digital pathology imaging of tumor tissue slides is becoming a routine clinical procedure for cancer diagnosis. This process produces massive imaging data that capture histological details in high resolution. Recent developments in deep-learning methods have enabled us to automatically detect and characterize the tumor regions in pathology images at large scale. From each identified tumor region, we extracted 30 well-defined descriptors that quantify its shape, geometry, and topology. We demonstrated how those descriptor features were associated with patient survival outcome in lung adenocarcinoma patients from the National Lung Screening Trial (n=143). Besides, a descriptor-based prognostic model was developed and validated in an independent patient cohort from The Cancer Genome Atlas Program program (n=318). This study proposes new insights into the relationship between tumor shape, geometrical, and topological features and patient prognosis. We provide software in the form of R code on GitHub: https://github.com/estfernandez/Slide_Image_Segmentation_and_Extraction.

Cong Zhang, Huinan Zeng, Huang Liu et al.

This study investigates whether the phonological features derived from the Featurally Underspecified Lexicon model can be applied in text-to-speech systems to generate native and non-native speech in English and Mandarin. We present a mapping of ARPABET/pinyin to SAMPA/SAMPA-SC and then to phonological features. This mapping was tested for whether it could lead to the successful generation of native, non-native, and code-switched speech in the two languages. We ran two experiments, one with a small dataset and one with a larger dataset. The results supported that phonological features could be used as a feasible input system for languages in or not in the train data, although further investigation is needed to improve model performance. The results lend support to FUL by presenting successfully synthesised output, and by having the output carrying a source-language accent when synthesising a language not in the training data. The TTS process stimulated human second language acquisition process and thus also confirm FUL's ability to account for acquisition.

Cong Zhang, Jian Zhu

Generating synthesised singing voice with models trained on speech data has many advantages due to the models' flexibility and controllability. However, since the information about the temporal relationship between segments and beats are lacking in speech training data, the synthesised singing may sound off-beat at times. Therefore, the availability of the information on the temporal relationship between speech segments and music beats is crucial. The current study investigated the segment-beat synchronisation in singing data, with hypotheses formed based on the linguistics theories of P-centre and sonority hierarchy. A Mandarin corpus and an English corpus of professional singing data were manually annotated and analysed. The results showed that the presence of musical beats was more dependent on segment duration than sonority. However, the sonority hierarchy and the P-centre theory were highly related to the location of beats. Mandarin and English demonstrated cross-linguistic variations despite exhibiting common patterns.