Yun Wang

Jason Fong, Yun Wang, Prabhav Agrawal et al.

Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording. Recent work has used neural models to produce edited speech that is similar to the original speech in terms of clarity, speaker identity, and prosody. However, one limitation of prior work is the usage of finetuning to optimise performance: this requires further model training on data from the target speaker, which is a costly process that may incorporate potentially sensitive data into server-side models. In contrast, this work focuses on the zero-shot approach which avoids finetuning altogether, and instead uses pretrained speaker verification embeddings together with a jointly trained reference encoder to encode utterance-level information that helps capture aspects such as speaker identity and prosody. Subjective listening tests find that both utterance embeddings and a reference encoder improve the continuity of speaker identity and prosody between the edited synthetic speech and unedited original recording in the zero-shot setting.

Yun Wang, Lingyun Yang, Senhao Yu et al.

Mixture-of-Experts (MoE) architectures scale language models by activating only a subset of specialized expert networks for each input token, thereby reducing the number of floating-point operations. However, the growing size of modern MoE models causes their full parameter sets to exceed GPU memory capacity; for example, Mixtral-8x7B has 45 billion parameters and requires 87 GB of memory even though only 14 billion parameters are used per token. Existing systems alleviate this limitation by offloading inactive experts to CPU memory, but transferring experts across the PCIe interconnect incurs significant latency (about 10 ms). Prefetching heuristics aim to hide this latency by predicting which experts are needed, but prefetch failures introduce significant stalls and amplify inference latency. In the event of a prefetch failure, prior work offers two primary solutions: either fetch the expert on demand, which incurs a long stall due to the PCIe bottleneck, or drop the expert from the computation, which significantly degrades model accuracy. The critical challenge, therefore, is to maintain both high inference speed and model accuracy when prefetching fails.

Sangeeta Srivastava, Yun Wang, Andros Tjandra et al.

Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have comprehensively analyzed audio representation learning for non-speech audio tasks. In this paper, we propose a self-supervised audio representation learning method and apply it to a variety of downstream non-speech audio tasks. We combine the well-known wav2vec 2.0 framework, which has shown success in self-supervised learning for speech tasks, with parameter-efficient conformer architectures. Our self-supervised pre-training can reduce the need for labeled data by two-thirds. On the AudioSet benchmark, we achieve a mean average precision (mAP) score of 0.415, which is a new state-of-the-art on this dataset through audio-only self-supervised learning. Our fine-tuned conformers also surpass or match the performance of previous systems pre-trained in a supervised way on several downstream tasks. We further discuss the important design considerations for both pre-training and fine-tuning.

Ashutosh Pandey, Chunxi Liu, Yun Wang et al.

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and find it helpful for ASR in two ways: a data augmentation technique, and a preprocessing frontend. In using it for ASR data augmentation, we exploit a KL divergence based consistency loss that is computed between the ASR outputs of original and enhanced utterances. In using speech enhancement as an effective ASR frontend, we propose a three-step training scheme based on model pretraining and feature selection. We evaluate our proposed techniques on a challenging social media English video dataset, and achieve an average relative improvement of 11.2% with speech enhancement based data augmentation, 8.3% with enhancement based preprocessing, and 13.4% when combining both.

Yun Wang, Tong Zhang, Zhen Cui et al.

Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task by introducing label dependencies based on statistical label co-occurrence of data. However, in previous methods, label correlation is computed based on statistical information of data and therefore the same for all samples, and this makes graph inference on labels insufficient to handle huge variations among numerous image instances. In this paper, we propose an instance-aware graph convolutional neural network (IA-GCN) framework for multi-label classification. As a whole, two fused branches of sub-networks are involved in the framework: a global branch modeling the whole image and a region-based branch exploring dependencies among regions of interests (ROIs). For label diffusion of instance-awareness in graph convolution, rather than using the statistical label correlation alone, an image-dependent label correlation matrix (LCM), fusing both the statistical LCM and an individual one of each image instance, is constructed for graph inference on labels to inject adaptive information of label-awareness into the learned features of the model. Specifically, the individual LCM of each image is obtained by mining the label dependencies based on the scores of labels about detected ROIs. In this process, considering the contribution differences of ROIs to multi-label classification, variational inference is introduced to learn adaptive scaling factors for those ROIs by considering their complex distribution. Finally, extensive experiments on MS-COCO and VOC datasets show that our proposed approach outperforms existing state-of-the-art methods.

Kun Han, Junwen Chen, Hui Zhang et al.

In this paper we present DELTA, a deep learning based language technology platform. DELTA is an end-to-end platform designed to solve industry level natural language and speech processing problems. It integrates most popular neural network models for training as well as comprehensive deployment tools for production. DELTA aims to provide easy and fast experiences for using, deploying, and developing natural language processing and speech models for both academia and industry use cases. We demonstrate the reliable performance with DELTA on several natural language processing and speech tasks, including text classification, named entity recognition, natural language inference, speech recognition, speaker verification, etc. DELTA has been used for developing several state-of-the-art algorithms for publications and delivering real production to serve millions of users.

Ke Xu, Yun Wang, Leni Yang et al.

Detecting and analyzing potential anomalous performances in cloud computing systems is essential for avoiding losses to customers and ensuring the efficient operation of the systems. To this end, a variety of automated techniques have been developed to identify anomalies in cloud computing performance. These techniques are usually adopted to track the performance metrics of the system (e.g., CPU, memory, and disk I/O), represented by a multivariate time series. However, given the complex characteristics of cloud computing data, the effectiveness of these automated methods is affected. Thus, substantial human judgment on the automated analysis results is required for anomaly interpretation. In this paper, we present a unified visual analytics system named CloudDet to interactively detect, inspect, and diagnose anomalies in cloud computing systems. A novel unsupervised anomaly detection algorithm is developed to identify anomalies based on the specific temporal patterns of the given metrics data (e.g., the periodic pattern), the results of which are visualized in our system to indicate the occurrences of anomalies. Rich visualization and interaction designs are used to help understand the anomalies in the spatial and temporal context. We demonstrate the effectiveness of CloudDet through a quantitative evaluation, two case studies with real-world data, and interviews with domain experts.

Shao-Yen Tseng, Juncheng Li, Yun Wang et al.

State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale datasets where fine resolution annotations are too expensive to obtain. In this paper, we propose a small-footprint multiple instance learning (MIL) framework for multi-class AED using weakly annotated labels. The proposed MIL framework uses audio embeddings extracted from a pre-trained convolutional neural network as input features. We show that by using audio embeddings the MIL framework can be implemented using a simple DNN with performance comparable to recurrent neural networks. We evaluate our approach by training an audio tagging system using a subset of AudioSet, which is a large collection of weakly labeled YouTube video excerpts. Combined with a late-fusion approach, we improve the F1 score of a baseline audio tagging system by 17%. We show that audio embeddings extracted by the convolutional neural networks significantly boost the performance of all MIL models. This framework reduces the model complexity of the AED system and is suitable for applications where computational resources are limited.