arXiv subjects

Thomas Fang Zheng

Publications and source records attributed to Thomas Fang Zheng.

35 records · Page 2Linked to original sources

arXiv2018

Deep factorization for speech signal

Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors. An intuitive idea is to factorize each speech frame into individual informative factors, though it turns out to be highly difficult. Recently, we found that speaker traits, which were assumed to be long-term distributional properties, are actually short-time patterns, and can be learned by a carefully designed deep neural network (DNN). This discovery motivated a cascade deep factorization (CDF) framework that will be presented in this paper. The proposed framework infers speech factors in a sequential way, where factors previously inferred are used as conditional variables when inferring other factors. We will show that this approach can effectively factorize speech signals, and using these factors, the original speech spectrum can be recovered with a high accuracy. This factorization and reconstruction approach provides potential values for many speech processing tasks, e.g., speaker recognition and emotion recognition, as will be demonstrated in the paper.

eess.AS↗

arXiv2017

Enhanced Neural Machine Translation by Learning from Draft

Neural machine translation (NMT) has recently achieved impressive results. A potential problem of the existing NMT algorithm, however, is that the decoding is conducted from left to right, without considering the right context. This paper proposes an two-stage approach to solve the problem. In the first stage, a conventional attention-based NMT system is used to produce a draft translation, and in the second stage, a novel double-attention NMT system is used to refine the translation, by looking at the original input as well as the draft translation. This drafting-and-refinement can obtain the right-context information from the draft, hence producing more consistent translations. We evaluated this approach using two Chinese-English translation tasks, one with 44k pairs and 1M pairs respectively. The experiments showed that our approach achieved positive improvements over the conventional NMT system: the improvements are 2.4 and 0.9 BLEU points on the small-scale and large-scale tasks, respectively.

cs.CL↗

arXiv2017

Deep Speaker Verification: Do We Need End to End?

End-to-end learning treats the entire system as a whole adaptable black box, which, if sufficient data are available, may learn a system that works very well for the target task. This principle has recently been applied to several prototype research on speaker verification (SV), where the feature learning and classifier are learned together with an objective function that is consistent with the evaluation metric. An opposite approach to end-to-end is feature learning, which firstly trains a feature learning model, and then constructs a back-end classifier separately to perform SV. Recently, both approaches achieved significant performance gains on SV, mainly attributed to the smart utilization of deep neural networks. However, the two approaches have not been carefully compared, and their respective advantages have not been well discussed. In this paper, we compare the end-to-end and feature learning approaches on a text-independent SV task. Our experiments on a dataset sampled from the Fisher database and involving 5,000 speakers demonstrated that the feature learning approach outperformed the end-to-end approach. This is a strong support for the feature learning approach, at least with data and computation resources similar to ours.

cs.SD↗

arXiv2017

Cross-lingual Speaker Verification with Deep Feature Learning

Existing speaker verification (SV) systems often suffer from performance degradation if there is any language mismatch between model training, speaker enrollment, and test. A major cause of this degradation is that most existing SV methods rely on a probabilistic model to infer the speaker factor, so any significant change on the distribution of the speech signal will impact the inference. Recently, we proposed a deep learning model that can learn how to extract the speaker factor by a deep neural network (DNN). By this feature learning, an SV system can be constructed with a very simple back-end model. In this paper, we investigate the robustness of the feature-based SV system in situations with language mismatch. Our experiments were conducted on a complex cross-lingual scenario, where the model training was in English, and the enrollment and test were in Chinese or Uyghur. The experiments demonstrated that the feature-based system outperformed the i-vector system with a large margin, particularly with language mismatch between enrollment and test.

cs.SD↗

arXiv2017

A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification

For practical automatic speaker verification (ASV) systems, replay attack poses a true risk. By replaying a pre-recorded speech signal of the genuine speaker, ASV systems tend to be easily fooled. An effective replay detection method is therefore highly desirable. In this study, we investigate a major difficulty in replay detection: the over-fitting problem caused by variability factors in speech signal. An F-ratio probing tool is proposed and three variability factors are investigated using this tool: speaker identity, speech content and playback & recording device. The analysis shows that device is the most influential factor that contributes the highest over-fitting risk. A frequency warping approach is studied to alleviate the over-fitting problem, as verified on the ASV-spoof 2017 database.

cs.SD↗

arXiv2016

System Combination for Short Utterance Speaker Recognition

For text-independent short-utterance speaker recognition (SUSR), the performance often degrades dramatically. This paper presents a combination approach to the SUSR tasks with two phonetic-aware systems: one is the DNN-based i-vector system and the other is our recently proposed subregion-based GMM-UBM system. The former employs phone posteriors to construct an i-vector model in which the shared statistics offers stronger robustness against limited test data, while the latter establishes a phone-dependent GMM-UBM system which represents speaker characteristics with more details. A score-level fusion is implemented to integrate the respective advantages from the two systems. Experimental results show that for the text-independent SUSR task, both the DNN-based i-vector system and the subregion-based GMM-UBM system outperform their respective baselines, and the score-level system combination delivers performance improvement.

cs.CL↗

arXiv2016

Decision Making Based on Cohort Scores for Speaker Verification

Decision making is an important component in a speaker verification system. For the conventional GMM-UBM architecture, the decision is usually conducted based on the log likelihood ratio of the test utterance against the GMM of the claimed speaker and the UBM. This single-score decision is simple but tends to be sensitive to the complex variations in speech signals (e.g. text content, channel, speaking style, etc.). In this paper, we propose a decision making approach based on multiple scores derived from a set of cohort GMMs (cohort scores). Importantly, these cohort scores are not simply averaged as in conventional cohort methods; instead, we employ a powerful discriminative model as the decision maker. Experimental results show that the proposed method delivers substantial performance improvement over the baseline system, especially when a deep neural network (DNN) is used as the decision maker, and the DNN input involves some statistical features derived from the cohort scores.

cs.SD↗

arXiv2016

Binary Speaker Embedding

The popular i-vector model represents speakers as low-dimensional continuous vectors (i-vectors), and hence it is a way of continuous speaker embedding. In this paper, we investigate binary speaker embedding, which transforms i-vectors to binary vectors (codes) by a hash function. We start from locality sensitive hashing (LSH), a simple binarization approach where binary codes are derived from a set of random hash functions. A potential problem of LSH is that the randomly sampled hash functions might be suboptimal. We therefore propose an improved Hamming distance learning approach, where the hash function is learned by a variable-sized block training that projects each dimension of the original i-vectors to variable-sized binary codes independently. Our experiments show that binary speaker embedding can deliver competitive or even better results on both speaker verification and identification tasks, while the memory usage and the computation cost are significantly reduced.

cs.SD↗

arXiv2016

Max-margin Metric Learning for Speaker Recognition

Probabilistic linear discriminant analysis (PLDA) is a popular normalization approach for the i-vector model, and has delivered state-of-the-art performance in speaker recognition. A potential problem of the PLDA model, however, is that it essentially assumes Gaussian distributions over speaker vectors, which is not always true in practice. Additionally, the objective function is not directly related to the goal of the task, e.g., discriminating true speakers and imposters. In this paper, we propose a max-margin metric learning approach to solve the problems. It learns a linear transform with a criterion that the margin between target and imposter trials are maximized. Experiments conducted on the SRE08 core test show that compared to PLDA, the new approach can obtain comparable or even better performance, though the scoring is simply a cosine computation.

cs.SD↗

arXiv2015

Transfer Learning for Speech and Language Processing

Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used to recognize speech in another language, with little or no re-training data. Transfer learning is closely related to multi-task learning (cross-lingual vs. multilingual), and is traditionally studied in the name of `model adaptation'. Recent advance in deep learning shows that transfer learning becomes much easier and more effective with high-level abstract features learned by deep models, and the `transfer' can be conducted not only between data distributions and data types, but also between model structures (e.g., shallow nets and deep nets) or even model types (e.g., Bayesian models and neural models). This review paper summarizes some recent prominent research towards this direction, particularly for speech and language processing. We also report some results from our group and highlight the potential of this very interesting research field.

cs.CL↗

arXiv2015

Parallel Knowledge Embedding with MapReduce on a Multi-core Processor

This article firstly attempts to explore parallel algorithms of learning distributed representations for both entities and relations in large-scale knowledge repositories with {\it MapReduce} programming model on a multi-core processor. We accelerate the training progress of a canonical knowledge embedding method, i.e. {\it translating embedding} ({\bf TransE}) model, by dividing a whole knowledge repository into several balanced subsets, and feeding each subset into an individual core where local embeddings can concurrently run updating during the {\it Map} phase. However, it usually suffers from inconsistent low-dimensional vector representations of the same key, which are collected from different {\it Map} workers, and further leads to conflicts when conducting {\it Reduce} to merge the various vectors associated with the same key. Therefore, we try several strategies to acquire the merged embeddings which may not only retain the performance of {\it entity inference}, {\it relation prediction}, and even {\it triplet classification} evaluated by the single-thread {\bf TransE} on several well-known knowledge bases such as Freebase and NELL, but also scale up the learning speed along with the number of cores within a processor. So far, the empirical studies show that we could achieve comparable results as the single-thread {\bf TransE} performs by the {\it stochastic gradient descend} (SGD) algorithm, as well as increase the training speed multiple times via adapting the {\it batch gradient descend} (BGD) algorithm for {\it MapReduce} paradigm.

cs.DC↗

arXiv2015

Distant Supervision for Entity Linking

Entity linking is an indispensable operation of populating knowledge repositories for information extraction. It studies on aligning a textual entity mention to its corresponding disambiguated entry in a knowledge repository. In this paper, we propose a new paradigm named distantly supervised entity linking (DSEL), in the sense that the disambiguated entities that belong to a huge knowledge repository (Freebase) are automatically aligned to the corresponding descriptive webpages (Wiki pages). In this way, a large scale of weakly labeled data can be generated without manual annotation and fed to a classifier for linking more newly discovered entities. Compared with traditional paradigms based on solo knowledge base, DSEL benefits more via jointly leveraging the respective advantages of Freebase and Wikipedia. Specifically, the proposed paradigm facilitates bridging the disambiguated labels (Freebase) of entities and their textual descriptions (Wikipedia) for Web-scale entities. Experiments conducted on a dataset of 140,000 items and 60,000 features achieve a baseline F1-measure of 0.517. Furthermore, we analyze the feature performance and improve the F1-measure to 0.545.

cs.CL↗

arXiv2015

Deep Speaker Vectors for Semi Text-independent Speaker Verification

Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker verification. This new method has been tested on text-dependent speaker verification tasks, and improvement was reported when combined with the conventional i-vector method. This paper extends the d-vector approach to semi text-independent speaker verification tasks, i.e., the text of the speech is in a limited set of short phrases. We explore various settings of the DNN structure used for d-vector extraction, and present a phone-dependent training which employs the posterior features obtained from an ASR system. The experimental results show that it is possible to apply d-vectors on semi text-independent speaker recognition, and the phone-dependent training improves system performance.

cs.CL↗

arXiv2015

Probabilistic Belief Embedding for Knowledge Base Completion

This paper contributes a novel embedding model which measures the probability of each belief $\langle h,r,t,m\rangle$ in a large-scale knowledge repository via simultaneously learning distributed representations for entities ($h$ and $t$), relations ($r$), and the words in relation mentions ($m$). It facilitates knowledge completion by means of simple vector operations to discover new beliefs. Given an imperfect belief, we can not only infer the missing entities, predict the unknown relations, but also tell the plausibility of the belief, just leveraging the learnt embeddings of remaining evidences. To demonstrate the scalability and the effectiveness of our model, we conduct experiments on several large-scale repositories which contain millions of beliefs from WordNet, Freebase and NELL, and compare it with other cutting-edge approaches via competing the performances assessed by the tasks of entity inference, relation prediction and triplet classification with respective metrics. Extensive experimental results show that the proposed model outperforms the state-of-the-arts with significant improvements.

cs.AI↗

arXiv2015

Large Margin Nearest Neighbor Embedding for Knowledge Representation

Traditional way of storing facts in triplets ({\it head\_entity, relation, tail\_entity}), abbreviated as ({\it h, r, t}), makes the knowledge intuitively displayed and easily acquired by mankind, but hardly computed or even reasoned by AI machines. Inspired by the success in applying {\it Distributed Representations} to AI-related fields, recent studies expect to represent each entity and relation with a unique low-dimensional embedding, which is different from the symbolic and atomic framework of displaying knowledge in triplets. In this way, the knowledge computing and reasoning can be essentially facilitated by means of a simple {\it vector calculation}, i.e. ${\bf h} + {\bf r} \approx {\bf t}$. We thus contribute an effective model to learn better embeddings satisfying the formula by pulling the positive tail entities ${\bf t^{+}}$ to get together and close to {\bf h} + {\bf r} ({\it Nearest Neighbor}), and simultaneously pushing the negatives ${\bf t^{-}}$ away from the positives ${\bf t^{+}}$ via keeping a {\it Large Margin}. We also design a corresponding learning algorithm to efficiently find the optimal solution based on {\it Stochastic Gradient Descent} in iterative fashion. Quantitative experiments illustrate that our approach can achieve the state-of-the-art performance, compared with several latest methods on some benchmark datasets for two classical applications, i.e. {\it Link prediction} and {\it Triplet classification}. Moreover, we analyze the parameter complexities among all the evaluated models, and analytical results indicate that our model needs fewer computational resources on outperforming the other methods.

cs.AI↗

arXiv2015

Learning Embedding Representations for Knowledge Inference on Imperfect and Incomplete Repositories

This paper considers the problem of knowledge inference on large-scale imperfect repositories with incomplete coverage by means of embedding entities and relations at the first attempt. We propose IIKE (Imperfect and Incomplete Knowledge Embedding), a probabilistic model which measures the probability of each belief, i.e. $\langle h,r,t\rangle$, in large-scale knowledge bases such as NELL and Freebase, and our objective is to learn a better low-dimensional vector representation for each entity ($h$ and $t$) and relation ($r$) in the process of minimizing the loss of fitting the corresponding confidence given by machine learning (NELL) or crowdsouring (Freebase), so that we can use $||{\bf h} + {\bf r} - {\bf t}||$ to assess the plausibility of a belief when conducting inference. We use subsets of those inexact knowledge bases to train our model and test the performances of link prediction and triplet classification on ground truth beliefs, respectively. The results of extensive experiments show that IIKE achieves significant improvement compared with the baseline and state-of-the-art approaches.

cs.AI↗

arXiv2014

Errata: Distant Supervision for Relation Extraction with Matrix Completion

The essence of distantly supervised relation extraction is that it is an incomplete multi-label classification problem with sparse and noisy features. To tackle the sparsity and noise challenges, we propose solving the classification problem using matrix completion on factorized matrix of minimized rank. We formulate relation classification as completing the unknown labels of testing items (entity pairs) in a sparse matrix that concatenates training and testing textual features with training labels. Our algorithmic framework is based on the assumption that the rank of item-by-feature and item-by-label joint matrix is low. We apply two optimization models to recover the underlying low-rank matrix leveraging the sparsity of feature-label matrix. The matrix completion problem is then solved by the fixed point continuation (FPC) algorithm, which can find the global optimum. Experiments on two widely used datasets with different dimensions of textual features demonstrate that our low-rank matrix completion approach significantly outperforms the baseline and the state-of-the-art methods.

cs.CL↗