Searcharxiv⌕ Search

arXiv subjects

Ke Ding

Publications and source records attributed to Ke Ding.

44 records · Page 3Linked to original sources
arXiv2022

CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR

History and future contextual information are known to be important for accurate acoustic modeling. However, acquiring future context brings latency for streaming ASR. In this paper, we propose a new framework - Chunking, Simulating Future Context and Decoding (CUSIDE) for streaming speech recognition. A new simulation module is introduced to recursively simulate the future contextual frames, without waiting for future context. The simulation module is jointly trained with the ASR model using a self-supervised loss; the ASR model is optimized with the usual ASR loss, e.g., CTC-CRF as used in our experiments. Experiments show that, compared to using real future frames as right context, using simulated future context can drastically reduce latency while maintaining recognition accuracy. With CUSIDE, we obtain new state-of-the-art streaming ASR results on the AISHELL-1 dataset.

eess.AS↗
arXiv2022

Two-Stream UNET Networks for Semantic Segmentation in Medical Images

Recent advances of semantic image segmentation greatly benefit from deeper and larger Convolutional Neural Network (CNN) models. Compared to image segmentation in the wild, properties of both medical images themselves and of existing medical datasets hinder training deeper and larger models because of overfitting. To this end, we propose a novel two-stream UNET architecture for automatic end-to-end medical image segmentation, in which intensity value and gradient vector flow (GVF) are two inputs for each stream, respectively. We demonstrate that two-stream CNNs with more low-level features greatly benefit semantic segmentation for imperfect medical image datasets. Our proposed two-stream networks are trained and evaluated on the popular medical image segmentation benchmarks, and the results are competitive with the state of the art. The code will be released soon.

cs.CV↗
arXiv2022

Unifying Cosine and PLDA Back-ends for Speaker Verification

State-of-art speaker verification (SV) systems use a back-end model to score the similarity of speaker embeddings extracted from a neural network model. The commonly used back-end models are the cosine scoring and the probabilistic linear discriminant analysis (PLDA) scoring. With the recently developed neural embeddings, the theoretically more appealing PLDA approach is found to have no advantage against or even be inferior the simple cosine scoring in terms of SV system performance. This paper presents an investigation on the relation between the two scoring approaches, aiming to explain the above counter-intuitive observation. It is shown that the cosine scoring is essentially a special case of PLDA scoring. In other words, by properly setting the parameters of PLDA, the two back-ends become equivalent. As a consequence, the cosine scoring not only inherits the basic assumptions for the PLDA but also introduces additional assumptions on the properties of input embeddings. Experiments show that the dimensional independence assumption required by the cosine scoring contributes most to the performance gap between the two methods under the domain-matched condition. When there is severe domain mismatch and the dimensional independence assumption does not hold, the PLDA would perform better than the cosine for domain adaptation.

cs.SD↗
arXiv2021

Dynamic-TinyBERT: Boost TinyBERT's Inference Efficiency by Dynamic Sequence Length

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. TinyBERT addresses the computational efficiency by self-distilling BERT into a smaller transformer representation having fewer layers and smaller internal embedding. However, TinyBERT's performance drops when we reduce the number of layers by 50%, and drops even more abruptly when we reduce the number of layers by 75% for advanced NLP tasks such as span question answering. Additionally, a separate model must be trained for each inference scenario with its distinct computational budget. In this work we present Dynamic-TinyBERT, a TinyBERT model that utilizes sequence-length reduction and Hyperparameter Optimization for enhanced inference efficiency per any computational budget. Dynamic-TinyBERT is trained only once, performing on-par with BERT and achieving an accuracy-speedup trade-off superior to any other efficient approaches (up to 3.3x with <1% loss-drop). Upon publication, the code to reproduce our work will be open-sourced.

cs.CL↗
arXiv2020

Climate change adaption in Chinese ancient architecture

As an important symbol of civilization and culture, architectures originally were built for sheltering human beings from weather disasters and therefore should be affected by climate change, particularly the associated change in the occurrence of extreme weather events. However, although meteorology has been considered as a factor in modern architecture design, it remains unclear whether and how the ancients adapted to climate change from the perspective of architecture design, particularly on a millennium time scale. Here we show that the periodic change and trend of the roof slope of ancient architectures in northern China clearly demonstrate the climate change adaptation over the past thousand years. We show that the snowfall fluctuation caused by the paleo-climate change was an essential driving factor within the roof modification process of ancient Chinese timber architecture. Our study indicates that climate change may act as a much more important factor on human behaviour than we ever thought.

physics.ao-ph↗
arXiv2020

Learning Speaker Embedding with Momentum Contrast

Speaker verification can be formulated as a representation learning task, where speaker-discriminative embeddings are extracted from utterances of variable lengths. Momentum Contrast (MoCo) is a recently proposed unsupervised representation learning framework, and has shown its effectiveness for learning good feature representation for downstream vision tasks. In this work, we apply MoCo to learn speaker embedding from speech segments. We explore MoCo for both unsupervised learning and pretraining settings. In the unsupervised scenario, embedding is learned by MoCo from audio data without using any speaker specific information. On a large scale dataset with $2,500$ speakers, MoCo can achieve EER $4.275\%$ trained unsupervisedly, and the EER can decrease further to $3.58\%$ if extra unlabelled data are used. In the pretraining scenario, encoder trained by MoCo is used to initialize the downstream supervised training. With finetuning on the MoCo trained model, the equal error rate (EER) reduces $13.7\%$ relative ($1.44\%$ to $1.242\%$) compared to a carefully tuned baseline training from scratch. Comparative study confirms the effectiveness of MoCo learning good speaker embedding.

cs.CL↗
arXiv2014

A CUDA-Based Real Parameter Optimization Benchmark

Benchmarking is key for developing and comparing optimization algorithms. In this paper, a CUDA-based real parameter optimization benchmark (cuROB) is introduced. Test functions of diverse properties are included within cuROB and implemented efficiently with CUDA. Speedup of one order of magnitude can be achieved in comparison with CPU-based benchmark of CEC'14.

cs.NE↗