arXiv subjects

Jianhua Tao

Publications and source records attributed to Jianhua Tao.

At least 145 records · Page 8Linked to original sources

arXiv2022

MixKG: Mixing for harder negative samples in knowledge graph

Knowledge graph embedding~(KGE) aims to represent entities and relations into low-dimensional vectors for many real-world applications. The representations of entities and relations are learned via contrasting the positive and negative triplets. Thus, high-quality negative samples are extremely important in KGE. However, the present KGE models either rely on simple negative sampling methods, which makes it difficult to obtain informative negative triplets; or employ complex adversarial methods, which requires more training data and strategies. In addition, these methods can only construct negative triplets using the existing entities, which limits the potential to explore harder negative triplets. To address these issues, we adopt mixing operation in generating harder negative samples for knowledge graphs and introduce an inexpensive but effective method called MixKG. Technically, MixKG first proposes two kinds of criteria to filter hard negative triplets among the sampled negatives: based on scoring function and based on correct entity similarity. Then, MixKG synthesizes harder negative samples via the convex combinations of the paired selected hard negatives. Experiments on two public datasets and four classical KGE methods show MixKG is superior to previous negative sampling algorithms.

cs.AI↗

arXiv2022

Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesis

End-to-end singing voice synthesis (SVS) is attractive due to the avoidance of pre-aligned data. However, the auto learned alignment of singing voice with lyrics is difficult to match the duration information in musical score, which will lead to the model instability or even failure to synthesize voice. To learn accurate alignment information automatically, this paper proposes an end-to-end SVS framework, named Singing-Tacotron. The main difference between the proposed framework and Tacotron is that the speech can be controlled significantly by the musical score's duration information. Firstly, we propose a global duration control attention mechanism for the SVS model. The attention mechanism can control each phoneme's duration. Secondly, a duration encoder is proposed to learn a set of global transition tokens from the musical score. These transition tokens can help the attention mechanism decide whether moving to the next phoneme or staying at each decoding step. Thirdly, to further improve the model's stability, a dynamic filter is designed to help the model overcome noise interference and pay more attention to local context information. Subjective and objective evaluation verify the effectiveness of the method. Furthermore, the role of global transition tokens and the effect of duration control are explored. Examples of experiments can be found at https://hairuo55.github.io/SingingTacotron.

cs.SD↗

arXiv2021

Knowledge graph enhanced recommender system

Knowledge Graphs (KGs) have shown great success in recommendation. This is attributed to the rich attribute information contained in KG to improve item and user representations as side information. However, existing knowledge-aware methods leverage attribute information at a coarse-grained level both in item and user side. In this paper, we proposed a novel attentive knowledge graph attribute network(AKGAN) to learn item attributes and user interests via attribute information in KG. Technically, AKGAN adopts a heterogeneous graph neural network framework, which has a different design between the first layer and the latter layer. With one attribute placed in the corresponding range of element-wise positions, AKGAN employs a novel interest-aware attention network, which releases the limitation that the sum of attention weight is 1, to model the complexity and personality of user interests towards attributes. Experimental results on three benchmark datasets show the effectiveness and explainability of AKGAN.

cs.IR↗

arXiv2021

Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT

Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because the decoder predicts text tokens (such as characters or words) in an autoregressive manner, it is difficult for an AED model to predict all tokens in parallel. This makes the inference speed relatively slow. We believe that because the encoder already captures the whole speech utterance, which has the token-level relationship implicitly, we can predict a token without explicitly autoregressive language modeling. When the prediction of a token does not rely on other tokens, the parallel prediction of all tokens in the sequence is realizable. Based on this idea, we propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once). The model consists of an encoder, a decoder, and a position dependent summarizer (PDS). The three modules are based on basic attention blocks. The encoder extracts high-level representations from the speech. The PDS uses positional encodings corresponding to tokens to convert the acoustic representations into token-level representations. The decoder further captures token-level relationships with the self-attention mechanism. At last, the probability distribution on the vocabulary is computed for each token position. Therefore, speech recognition is re-formulated as a position-wise classification problem. Further, we propose a cross-modal transfer learning method to refine semantics from a large-scale pre-trained language model BERT for improving the performance.

cs.CL↗

arXiv2021

Multi-Level Graph Contrastive Learning

Graph representation learning has attracted a surge of interest recently, whose target at learning discriminant embedding for each node in the graph. Most of these representation methods focus on supervised learning and heavily depend on label information. However, annotating graphs are expensive to obtain in the real world, especially in specialized domains (i.e. biology), as it needs the annotator to have the domain knowledge to label the graph. To approach this problem, self-supervised learning provides a feasible solution for graph representation learning. In this paper, we propose a Multi-Level Graph Contrastive Learning (MLGCL) framework for learning robust representation of graph data by contrasting space views of graphs. Specifically, we introduce a novel contrastive view - topological and feature space views. The original graph is first-order approximation structure and contains uncertainty or error, while the $k$NN graph generated by encoding features preserves high-order proximity. Thus $k$NN graph generated by encoding features not only provide a complementary view, but is more suitable to GNN encoder to extract discriminant representation. Furthermore, we develop a multi-level contrastive mode to preserve the local similarity and semantic similarity of graph-structured data simultaneously. Extensive experiments indicate MLGCL achieves promising results compared with the existing state-of-the-art graph representation learning methods on seven datasets.

cs.LG↗

arXiv2021

Continual Learning for Fake Audio Detection

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data. Fine-tuning and retraining from scratch have been applied to incorporate new data. However, fine-tuning leads to performance degradation on previous data. Retraining takes a lot of time and computation resources. Besides, previous data are unavailable due to privacy in some situations. To solve the above problems, this paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally. A knowledge distillation loss is introduced to loss function to preserve the memory of original model. Supposing the distribution of genuine voice is consistent among different scenarios, an extra embedding similarity loss is used as another constraint to further do a positive sample alignment. Experiments are conducted on the ASVspoof2019 dataset. The results show that our proposed method outperforms fine-tuning by the relative reduction of average equal error rate up to 81.62%.

cs.SD↗

arXiv2021

FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization

Transducer-based models, such as RNN-Transducer and transformer-transducer, have achieved great success in speech recognition. A typical transducer model decodes the output sequence conditioned on the current acoustic state and previously predicted tokens step by step. Statistically, The number of blank tokens in the prediction results accounts for nearly 90\% of all tokens. It takes a lot of computation and time to predict the blank tokens, but only the non-blank tokens will appear in the final output sequence. Therefore, we propose a method named fast-skip regularization, which tries to align the blank position predicted by a transducer with that predicted by a CTC model. During the inference, the transducer model can predict the blank tokens in advance by a simple CTC project layer without many complicated forward calculations of the transducer decoder and then skip them, which will reduce the computation and improve the inference speed greatly. All experiments are conducted on a public Chinese mandarin dataset AISHELL-1. The results show that the fast-skip regularization can indeed help the transducer model learn the blank position alignments. Besides, the inference with fast-skip can be speeded up nearly 4 times with only a little performance degradation.

eess.AS↗

arXiv2021

One In A Hundred: Select The Best Predicted Sequence from Numerous Candidates for Streaming Speech Recognition

The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it cannot capture the linguistic dependencies between the output tokens. Inspired by the success of two-pass end-to-end models, we introduce a transformer decoder and the two-stage inference method into the streaming CTC model. During inference, the CTC decoder first generates many candidates in a streaming fashion. Then the transformer decoder selects the best candidate based on the corresponding acoustic encoded states. The second-stage transformer decoder can be regarded as a conditional language model. We assume that a large enough number and enough diversity of candidates generated in the first stage can compensate the CTC model for the lack of language modeling ability. All the experiments are conducted on a Chinese Mandarin dataset AISHELL-1. The results show that our proposed model can implement streaming decoding in a fast and straightforward way. Our model can achieve up to a 20% reduction in the character error rate than the baseline CTC model. In addition, our model can also perform non-streaming inference with only a little performance degradation.

eess.AS↗

arXiv2021

TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition

The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded states, which is inefficient on GPUs. The non-autoregressive (NAR) models can get rid of the temporal dependency between the output tokens and predict the entire output tokens in at least one step. However, the NAR model still faces two major problems. On the one hand, there is still a great gap in performance between the NAR models and the advanced AR models. On the other hand, it's difficult for most of the NAR models to train and converge. To address these two problems, we propose a new model named the two-step non-autoregressive transformer(TSNAT), which improves the performance and accelerating the convergence of the NAR model by learning prior knowledge from a parameters-sharing AR model. Furthermore, we introduce the two-stage method into the inference process, which improves the model performance greatly. All the experiments are conducted on a public Chinese mandarin dataset ASIEHLL-1. The results show that the TSNAT can achieve a competitive performance with the AR model and outperform many complicated NAR models.

eess.AS↗

arXiv2021

Integrating Knowledge into End-to-End Speech Recognition from External Text-Only Data

Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because of the end-to-end training, an AED model is usually trained with speech-text paired data. It is challenging to incorporate external text-only data into AED models. Another issue of the AED model is that it does not use the right context of a text token while predicting the token. To alleviate the above two issues, we propose a unified method called LST (Learn Spelling from Teachers) to integrate knowledge into an AED model from the external text-only data and leverage the whole context in a sentence. The method is divided into two stages. First, in the representation stage, a language model is trained on the text. It can be seen as that the knowledge in the text is compressed into the LM. Then, at the transferring stage, the knowledge is transferred to the AED model via teacher-student learning. To further use the whole context of the text sentence, we propose an LM called causal cloze completer (COR), which estimates the probability of a token, given both the left context and the right context of it. Therefore, with LST training, the AED model can leverage the whole context in the sentence. Different from fusion based methods, which use LM during decoding, the proposed method does not increase any extra complexity at the inference stage. We conduct experiments on two scales of public Chinese datasets AISHELL-1 and AISHELL-2. The experimental results demonstrate the effectiveness of leveraging external text-only data and the whole context in a sentence with our proposed method, compared with baseline hybrid systems and AED model based systems.

eess.AS↗

arXiv2020

Tucker decomposition-based Temporal Knowledge Graph Completion

Knowledge graphs have been demonstrated to be an effective tool for numerous intelligent applications. However, a large amount of valuable knowledge still exists implicitly in the knowledge graphs. To enrich the existing knowledge graphs, recent years witness that many algorithms for link prediction and knowledge graphs embedding have been designed to infer new facts. But most of these studies focus on the static knowledge graphs and ignore the temporal information that reflects the validity of knowledge. Developing the model for temporal knowledge graphs completion is an increasingly important task. In this paper, we build a new tensor decomposition model for temporal knowledge graphs completion inspired by the Tucker decomposition of order 4 tensor. We demonstrate that the proposed model is fully expressive and report state-of-the-art results for several public benchmarks. Additionally, we present several regularization schemes to improve the strategy and study their impact on the proposed model. Experimental studies on three temporal datasets (i.e. ICEWS2014, ICEWS2005-15, GDELT) justify our design and demonstrate that our model outperforms baselines with an explicit margin on link prediction task.

cs.AI↗

arXiv2020

Self-supervised Graph Representation Learning via Bootstrapping

Graph neural networks~(GNNs) apply deep learning techniques to graph-structured data and have achieved promising performance in graph representation learning. However, existing GNNs rely heavily on enough labels or well-designed negative samples. To address these issues, we propose a new self-supervised graph representation method: deep graph bootstrapping~(DGB). DGB consists of two neural networks: online and target networks, and the input of them are different augmented views of the initial graph. The online network is trained to predict the target network while the target network is updated with a slow-moving average of the online network, which means the online and target networks can learn from each other. As a result, the proposed DGB can learn graph representation without negative examples in an unsupervised manner. In addition, we summarize three kinds of augmentation methods for graph-structured data and apply them to the DGB. Experiments on the benchmark datasets show the DGB performs better than the current state-of-the-art methods and how the augmentation methods affect the performances.

cs.LG↗

arXiv2020

Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning

Recurrent neural networks (RNNs) have shown significant improvements in recent years for speech enhancement. However, the model complexity and inference time cost of RNNs are much higher than deep feed-forward neural networks (DNNs). Therefore, these limit the applications of speech enhancement. This paper proposes a deep time delay neural network (TDNN) for speech enhancement with full data learning. The TDNN has excellent potential for capturing long range temporal contexts, which utilizes a modular and incremental design. Besides, the TDNN preserves the feed-forward structure so that its inference cost is comparable to standard DNN. To make full use of the training data, we propose a full data learning method for speech enhancement. More specifically, we not only use the noisy-to-clean (input-to-target) to train the enhanced model, but also the clean-to-clean and noise-to-silence data. Therefore, all of the training data can be used to train the enhanced model. Our experiments are conducted on TIMIT dataset. Experimental results show that our proposed method could achieve a better performance than DNN and comparable even better performance than BLSTM. Meanwhile, compared with the BLSTM, the proposed method drastically reduce the inference time.

cs.SD↗

arXiv2020

Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However, these methods only utilize the enhanced feature as the input of the speech recognition component, which are affected by the speech distortion problem. In order to address this problem, this paper proposes a gated recurrent fusion (GRF) method with joint training framework for robust end-to-end ASR. The GRF algorithm is used to dynamically combine the noisy and enhanced features. Therefore, the GRF can not only remove the noise signals from the enhanced features, but also learn the raw fine structures from the noisy features so that it can alleviate the speech distortion. The proposed method consists of speech enhancement, GRF and speech recognition. Firstly, the mask based speech enhancement network is applied to enhance the input speech. Secondly, the GRF is applied to address the speech distortion problem. Thirdly, to improve the performance of ASR, the state-of-the-art speech transformer algorithm is used as the speech recognition component. Finally, the joint training framework is utilized to optimize these three components, simultaneously. Our experiments are conducted on an open-source Mandarin speech corpus called AISHELL-1. Experimental results show that the proposed method achieves the relative character error rate (CER) reduction of 10.04\% over the conventional joint enhancement and transformer method only using the enhanced features. Especially for the low signal-to-noise ratio (0 dB), our proposed method can achieves better performances with 12.67\% CER reduction, which suggests the potential of our proposed method.

cs.SD↗

arXiv2020

Decoupling Pronunciation and Language for End-to-end Code-switching Automatic Speech Recognition

Despite the recent significant advances witnessed in end-to-end (E2E) ASR system for code-switching, hunger for audio-text paired data limits the further improvement of the models' performance. In this paper, we propose a decoupled transformer model to use monolingual paired data and unpaired text data to alleviate the problem of code-switching data shortage. The model is decoupled into two parts: audio-to-phoneme (A2P) network and phoneme-to-text (P2T) network. The A2P network can learn acoustic pattern scenarios using large-scale monolingual paired data. Meanwhile, it generates multiple phoneme sequence candidates for single audio data in real-time during the training process. Then the generated phoneme-text paired data is used to train the P2T network. This network can be pre-trained with large amounts of external unpaired text data. By using monolingual data and unpaired text data, the decoupled transformer model reduces the high dependency on code-switching paired training data of E2E model to a certain extent. Finally, the two networks are optimized jointly through attention fusion. We evaluate the proposed method on the public Mandarin-English code-switching dataset. Compared with our transformer baseline, the proposed method achieves 18.14% relative mix error rate reduction.

cs.SD↗

arXiv2020

Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications. To address this issue, we propose a non-autoregressive end-to-end speech recognition system called LASO (listen attentively, and spell once). Because of the non-autoregressive property, LASO predicts a textual token in the sequence without the dependence on other tokens. Without beam-search, the one-pass propagation much reduces inference time cost of LASO. And because the model is based on the attention based feedforward structure, the computation can be implemented in parallel efficiently. We conduct experiments on publicly available Chinese dataset AISHELL-1. LASO achieves a character error rate of 6.4%, which outperforms the state-of-the-art autoregressive transformer model (6.7%). The average inference latency is 21 ms, which is 1/50 of the autoregressive transformer model.

eess.AS↗

arXiv2020

Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition

Non-autoregressive transformer models have achieved extremely fast inference speed and comparable performance with autoregressive sequence-to-sequence models in neural machine translation. Most of the non-autoregressive transformers decode the target sequence from a predefined-length mask sequence. If the predefined length is too long, it will cause a lot of redundant calculations. If the predefined length is shorter than the length of the target sequence, it will hurt the performance of the model. To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence. All the experiments are conducted on a public Chinese mandarin dataset AISHELL-1. The results show that the proposed model can accurately predict the length of the target sequence and achieve a competitive performance with the advanced transformers. What's more, the model even achieves a real-time factor of 0.0056, which exceeds all mainstream speech recognition models.

eess.AS↗

arXiv2020

Simultaneous Denoising and Dereverberation Using Deep Embedding Features

Monaural speech dereverberation is a very challenging task because no spatial cues can be used. When the additive noises exist, this task becomes more challenging. In this paper, we propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features, which is based on the deep clustering (DC). DC is a state-of-the-art method for speech separation that includes embedding learning and K-means clustering. As for our proposed method, it contains two stages: denoising and dereverberation. At the denoising stage, the DC network is leveraged to extract noise-free deep embedding features. These embedding features are generated from the anechoic speech and residual reverberation signals. They can represent the inferred spectral masking patterns of the desired signals, which are discriminative features. At the dereverberation stage, instead of using the unsupervised K-means clustering algorithm, another supervised neural network is utilized to estimate the anechoic speech from these deep embedding features. Finally, the denoising stage and dereverberation stage are optimized by the joint training method. Experimental results show that the proposed method outperforms the WPE and BLSTM baselines, especially in the low SNR condition.

eess.AS↗