Searcharxiv⌕ Search

arXiv subjects

Quan Wang

Publications and source records attributed to Quan Wang.

At least 163 records · Page 9Linked to original sources

Generalized End-to-End Loss for Speaker Verification

In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the GE2E loss function updates the network in a way that emphasizes examples that are difficult to verify at each step of the training process. Additionally, the GE2E loss does not require an initial stage of example selection. With these properties, our model with the new loss function decreases speaker verification EER by more than 10%, while reducing the training time by 60% at the same time. We also introduce the MultiReader technique, which allows us to do domain adaptation - training a more accurate model that supports multiple keywords (i.e. "OK Google" and "Hey Google") as well as multiple dialects.

eess.AS↗

VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents numerous challenges: It should improve the performance when the input signal consists of overlapped speech, and must not hurt the speech recognition performance under all other acoustic conditions. Besides, this model must be tiny, fast, and perform inference in a streaming fashion, in order to have minimal impact on CPU, memory, battery and latency. We propose novel techniques to meet these multi-faceted requirements, including using a new asymmetric loss, and adopting adaptive runtime suppression strength. We also show that such a model can be quantized as a 8-bit integer model and run in realtime.

eess.AS↗

ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech

Automatic speaker verification (ASV) is one of the most natural and convenient means of biometric person recognition. Unfortunately, just like all other biometric systems, ASV is vulnerable to spoofing, also referred to as "presentation attacks." These vulnerabilities are generally unacceptable and call for spoofing countermeasures or "presentation attack detection" systems. In addition to impersonation, ASV systems are vulnerable to replay, speech synthesis, and voice conversion attacks. The ASVspoof 2019 edition is the first to consider all three spoofing attack types within a single challenge. While they originate from the same source database and same underlying protocol, they are explored in two specific use case scenarios. Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques. Replay spoofing attacks within a physical access (PA) scenario are generated through carefully controlled simulations that support much more revealing analysis than possible previously. Also new to the 2019 edition is the use of the tandem detection cost function metric, which reflects the impact of spoofing and countermeasures on the reliability of a fixed ASV system. This paper describes the database design, protocol, spoofing attack implementations, and baseline ASV and countermeasure results. It also describes a human assessment on spoofed data in logical access. It was demonstrated that the spoofing data in the ASVspoof 2019 database have varied degrees of perceived quality and similarity to the target speakers, including spoofed data that cannot be differentiated from bona-fide utterances even by human subjects.

eess.AS↗

A Comparative Study on Polyp Classification using Convolutional Neural Networks

Colorectal cancer is the third most common cancer diagnosed in both men and women in the United States. Most colorectal cancers start as a growth on the inner lining of the colon or rectum, called 'polyp'. Not all polyps are cancerous, but some can develop into cancer. Early detection and recognition of the type of polyps is critical to prevent cancer and change outcomes. However, visual classification of polyps is challenging due to varying illumination conditions of endoscopy, variant texture, appearance, and overlapping morphology between polyps. More importantly, evaluation of polyp patterns by gastroenterologists is subjective leading to a poor agreement among observers. Deep convolutional neural networks have proven very successful in object classification across various object categories. In this work, we compare the performance of the state-of-the-art general object classification models for polyp classification. We trained a total of six CNN models end-to-end using a dataset of 157 video sequences composed of two types of polyps: hyperplastic and adenomatous. Our results demonstrate that the state-of-the-art CNN models can successfully classify polyps with an accuracy comparable or better than reported among gastroenterologists. The results of this study can guide future research in polyp classification.

cs.CV↗

Fast and Accurate: Structure Coherence Component for Face Alignment

In this paper, we propose a fast and accurate coordinate regression method for face alignment. Unlike most existing facial landmark regression methods which usually employ fully connected layers to convert feature maps into landmark coordinate, we present a structure coherence component to explicitly take the relation among facial landmarks into account. Due to the geometric structure of human face, structure coherence between different facial parts provides important cues for effectively localizing facial landmarks. However, the dense connection in the fully connected layers overuses such coherence, making the important cues unable to be distinguished from all connections. Instead, our structure coherence component leverages a dynamic sparse graph structure to passing features among the most related landmarks. Furthermore, we propose a novel objective function, named Soft Wing loss, to improve the accuracy. Extensive experiments on three popular benchmarks, including WFLW, COFW and 300W, demonstrate the effectiveness of the proposed method, achieving state-of-the-art performance with fast speed. Our approach is especially robust to challenging cases resulting in impressively low failure rate (0% and 2.88%) in COFW and WFLW datasets.

cs.CV↗

CoKE: Contextualized Knowledge Graph Embedding

Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, ignoring their intrinsic contextual nature, i.e., entities and relations may appear in different graph contexts, and accordingly, exhibit different properties. This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings. Two types of graph contexts are studied: edges and paths, both formulated as sequences of entities and relations. CoKE takes a sequence as input and uses a Transformer encoder to obtain contextualized representations. These representations are hence naturally adaptive to the input, capturing contextual meanings of entities and relations therein. Evaluation on a wide variety of public benchmarks verifies the superiority of CoKE in link prediction and path query answering. It performs consistently better than, or at least equally well as current state-of-the-art in almost every case, in particular offering an absolute improvement of 21.0% in H@10 on path query answering. Our code is available at \url{https://github.com/PaddlePaddle/Research/tree/master/KG/CoKE}.

cs.AI↗

FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos

Recently, facial landmark detection algorithms have achieved remarkable performance on static images. However, these algorithms are neither accurate nor stable in motion-blurred videos. The missing of structure information makes it difficult for state-of-the-art facial landmark detection algorithms to yield good results. In this paper, we propose a framework named FAB that takes advantage of structure consistency in the temporal dimension for facial landmark detection in motion-blurred videos. A structure predictor is proposed to predict the missing face structural information temporally, which serves as a geometry prior. This allows our framework to work as a virtuous circle. On one hand, the geometry prior helps our structure-aware deblurring network generates high quality deblurred images which lead to better landmark detection results. On the other hand, better landmark detection results help structure predictor generate better geometry prior for the next frame. Moreover, it is a flexible video-based framework that can incorporate any static image-based methods to provide a performance boost on video datasets. Extensive experiments on Blurred-300VW, the proposed Real-world Motion Blur (RWMB) datasets and 300VW demonstrate the superior performance to the state-of-the-art methods. Datasets and models will be publicly available at https://keqiangsun.github.io/projects/FAB/FAB.html.

cs.CV↗

Make a Face: Towards Arbitrary High Fidelity Face Manipulation

Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack of diversity. In this work, we propose Additive Focal Variational Auto-encoder (AF-VAE), a novel approach that can arbitrarily manipulate high-resolution face images using a simple yet effective model and only weak supervision of reconstruction and KL divergence losses. First, a novel additive Gaussian Mixture assumption is introduced with an unsupervised clustering mechanism in the structural latent space, which endows better disentanglement and boosts multi-modal representation with external memory. Second, to improve the perceptual quality of synthesized results, two simple strategies in architecture design are further tailored and discussed on the behavior of Human Visual System (HVS) for the first time, allowing for fine control over the model complexity and sample quality. Human opinion studies and new state-of-the-art Inception Score (IS) / Frechet Inception Distance (FID) demonstrate the superiority of our approach over existing algorithms, advancing both the fidelity and extremity of face manipulation task.

cs.CV↗

VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking

In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask. Our system significantly reduces the speech recognition WER on multi-speaker signals, with minimal WER degradation on single-speaker signals.

eess.AS↗

Coding Capacity of Purkinje Cells with Different Schemes of Morphological Reduction

The brain as a neuronal system has very complex structure with large diversity of neuronal types. The most basic complexity is seen from the structure of neuronal morphology, which usually has a complex tree-like structure with dendritic spines distributed in branches. For simulating a large-scale network with spiking neurons, the simple point neuron, such as integrate-and-fire neuron, is often used. However, recent experimental evidence suggests that the computational ability of a single neuron is largely enhanced by its morphological structure, in particular, by various types of dendritic dynamics. As morphology reduction of detailed biophysical models is one of classic questions for systems neuroscience, much effort has been taken to simulate a neuron with a few compartments to include the interaction between soma and dendritic spines. Yet, novel reduction methods are still needed to deal with complex dendritic tree. Here by using ten individual Purkinje cells of the cerebellum from three species of guinea-pig, mouse and rat, we consider four types of reduction methods and study their effects on the coding capacity of Purkinje cells in terms of firing rate, timing coding, spiking pattern, and modulated firing under different stimulation protocols. We find that there is a variation of reduction performance depending on individual cells and species, however, all reduction methods can preserve, to some degree, firing activity of the full model of Purkinje cell. Therefore, when stimulating large-scale network of neurons, one has to choose a proper type of reduced neuronal model depending on the questions addressed.

q-bio.NC↗

Fully Supervised Speaker Diarization

In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given extracted speaker-discriminative embeddings (a.k.a. d-vectors) from input utterances, each individual speaker is modeled by a parameter-sharing RNN, while the RNN states for different speakers interleave in the time domain. This RNN is naturally integrated with a distance-dependent Chinese restaurant process (ddCRP) to accommodate an unknown number of speakers. Our system is fully supervised and is able to learn from examples where time-stamped speaker labels are annotated. We achieved a 7.6% diarization error rate on NIST SRE 2000 CALLHOME, which is better than the state-of-the-art method using spectral clustering. Moreover, our method decodes in an online fashion while most state-of-the-art systems rely on offline clustering.

eess.AS↗

Tuplemax Loss for Language Identification

In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages. We want to model such prior knowledge into the way we train our neural networks, by replacing the commonly used softmax loss function with a novel loss function named tuplemax loss. As a matter of fact, a typical language identification system launched in North America has about 95% users who could speak no more than two languages. Using the tuplemax loss, our system achieved a 2.33% error rate, which is a relative 39.4% improvement over the 3.85% error rate of standard softmax loss method.

eess.AS↗

Sample Efficient Adaptive Text-to-Speech

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of training is not to produce a neural network with fixed weights, which is then deployed as a TTS system. Instead, the aim is to produce a network that requires few data at deployment time to rapidly adapt to new speakers. We introduce and benchmark three strategies: (i) learning the speaker embedding while keeping the WaveNet core fixed, (ii) fine-tuning the entire architecture with stochastic gradient descent, and (iii) predicting the speaker embedding with a trained neural network encoder. The experiments show that these approaches are successful at adapting the multi-speaker neural network to new speakers, obtaining state-of-the-art results in both sample naturalness and voice similarity with merely a few minutes of audio data from new speakers.

cs.LG↗

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which generates a mel spectrogram from text, conditioned on the speaker embedding; (3) an auto-regressive WaveNet-based vocoder that converts the mel spectrogram into a sequence of time domain waveform samples. We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker encoder to the new task, and is able to synthesize natural speech from speakers that were not seen during training. We quantify the importance of training the speaker encoder on a large and diverse speaker set in order to obtain the best generalization performance. Finally, we show that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.

cs.CL↗

A Time-domain Analog Weighted-sum Calculation Model for Extremely Low Power VLSI Implementation of Multi-layer Neural Networks

A time-domain analog weighted-sum calculation model is proposed based on an integrate-and-fire-type spiking neuron model. The proposed calculation model is applied to multi-layer feedforward networks, in which weighted summations with positive and negative weights are separately performed in each layer and summation results are then fed into the next layers without their subtraction operation. We also propose very large-scale integrated (VLSI) circuits to implement the proposed model. Unlike the conventional analog voltage or current mode circuits, the time-domain analog circuits use transient operation in charging/discharging processes to capacitors. Since the circuits can be designed without operational amplifiers, they can operate with extremely low power consumption. However, they have to use very high resistance devices on the order of G$\rm Ω$. We designed a proof-of-concept (PoC) CMOS VLSI chip to verify weighted-sum operation with the same weights and evaluated it by post-layout circuit simulation using 250-nm fabrication technology. High resistance operation was realized by using the subthreshold operation region of MOS transistors. Simulation results showed that energy efficiency for the weighted-sum calculation was 290~TOPS/W, more than one order of magnitude higher than that in state-of-the-art digital AI processors, even though the minimum width of interconnection used in the PoC chip was several times larger than that in such digital processors. If state-of-the-art VLSI technology is used to implement the proposed model, an energy efficiency of more than 1,000~TOPS/W will be possible. For practical applications, development of emerging analog memory devices such as ferroelectric-gate FETs is necessary.

cs.ET↗

An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN

Polyp has long been considered as one of the major etiologies to colorectal cancer which is a fatal disease around the world, thus early detection and recognition of polyps plays a crucial role in clinical routines. Accurate diagnoses of polyps through endoscopes operated by physicians becomes a challenging task not only due to the varying expertise of physicians, but also the inherent nature of endoscopic inspections. To facilitate this process, computer-aid techniques that emphasize fully-conventional image processing and novel machine learning enhanced approaches have been dedicatedly designed for polyp detection in endoscopic videos or images. Among all proposed algorithms, deep learning based methods take the lead in terms of multiple metrics in evolutions for algorithmic performance. In this work, a highly effective model, namely the faster region-based convolutional neural network (Faster R-CNN) is implemented for polyp detection. In comparison with the reported results of the state-of-the-art approaches on polyps detection, extensive experiments demonstrate that the Faster R-CNN achieves very competing results, and it is an efficient approach for clinical practice.

q-bio.TO↗

Look at Boundary: A Boundary-Aware Face Alignment Algorithm

We present a novel boundary-aware face alignment algorithm by utilising boundary lines as the geometric structure of a human face to help facial landmark localisation. Unlike the conventional heatmap based method and regression based method, our approach derives face landmarks from boundary lines which remove the ambiguities in the landmark definition. Three questions are explored and answered by this work: 1. Why using boundary? 2. How to use boundary? 3. What is the relationship between boundary estimation and landmarks localisation? Our boundary- aware face alignment algorithm achieves 3.49% mean error on 300-W Fullset, which outperforms state-of-the-art methods by a large margin. Our method can also easily integrate information from other datasets. By utilising boundary information of 300-W dataset, our method achieves 3.92% mean error with 0.39% failure rate on COFW dataset, and 1.25% mean error on AFLW-Full dataset. Moreover, we propose a new dataset WFLW to unify training and testing across different factors, including poses, expressions, illuminations, makeups, occlusions, and blurriness. Dataset and model will be publicly available at https://wywu.github.io/projects/LAB/LAB.html

cs.CV↗

Improving Knowledge Graph Embedding Using Simple Constraints

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Early works performed this task via simple models developed over KG triples. Recent attempts focused on either designing more complicated triple scoring models, or incorporating extra information beyond triples. This paper, by contrast, investigates the potential of using very simple constraints to improve KG embedding. We examine non-negativity constraints on entity representations and approximate entailment constraints on relation representations. The former help to learn compact and interpretable representations for entities. The latter further encode regularities of logical entailment between relations into their distributed representations. These constraints impose prior beliefs upon the structure of the embedding space, without negative impacts on efficiency or scalability. Evaluation on WordNet, Freebase, and DBpedia shows that our approach is simple yet surprisingly effective, significantly and consistently outperforming competitive baselines. The constraints imposed indeed improve model interpretability, leading to a substantially increased structuring of the embedding space. Code and data are available at https://github.com/iieir-km/ComplEx-NNE_AER.

cs.AI↗