14 accepted papers
Developing a reliable anomalous sound detection (ASD) system requires robustness to noise, adaptation to domain shifts, and effective performance with limited training data. Current leading methods rely on extensive labeled data for each target machine type to train feature extractors using Outlier-…
In self-supervised speaker verification, the quality of generated pseudo labels becomes a bottleneck for the performance. This work introduces a dynamic threshold within the iterative DIstillation with NO labels (DINO) framework. We employ a Gaussian Mixture Model (GMM) to model the loss distributio…
Studies on spoken language acquisition agents aim to understand the mechanism of human language learning and to realize it on computers. Existing open vocabulary agents first perform unsupervised word learning from speech signals to construct a word dictionary as a discrete action space and then con…
Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to utilize the unlabeled data more effectively since they either use…
As the core of task-oriented dialogue systems, dialogue state tracking (DST) is designed to track the dialogue state through the conversation between users and systems. Multi-domain DST has been an important challenge in which the dialogue states across multiple domains need to consider. In recent m…
Target-oriented Opinion Words Extraction (TOWE) is a fine-grained sentiment analysis task that aims to extract the corresponding opinion words of a given opinion target from the sentence. Recently, deep learning approaches have made remarkable progress on this task. Nevertheless, the TOWE task still…
In this paper we propose improvements to our recently proposed hybrid RNN-T/Attention architecture that includes a shared encoder followed by recurrent neural network-transducer (RNN-T) and triggered attention-based decoders (TAD). The use of triggered attention enables the attention-based decoder (…
Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural netw…
The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks. However, like other modern SSL algorithms, FixMatch uses a pre-defined constant threshold for all classes to select unlabeled data that contribute to the training, thus failing to cons…
Transfer learning from a multilingual model has shown favorable results on low-resource automatic speech recognition (ASR). However, full-model fine-tuning generates a separate model for every target language and is not suitable for deploying and maintaining in production. The key challenge lies in…
The process of spoken-language acquisition has been one of the topics of greatest interest to linguists for decades. By uti-lizing modern machine learning techniques, we simulated this process on computers, which helps to understand it and develop new possibilities of applying this concept on intell…
Computer simulations have facilitated our understanding of the dynamic behavior of the brain and the effect of the medical treatment such as deep brain stimulation. For improving the simulation model, it is essential to develop a method for optimizing parameters of a neuron model from available expe…
Automatic speech recognition (ASR) systems have achieved high recognition performance for several tasks. However, the performance of such systems is dependent on the tremendously costly development work of preparing vast amounts of task-matched transcribed speech data for supervised training. The ke…
Deep neural networks (DNNs) are constructed by considering highly complicated configurations including network structure and several tuning parameters (number of hidden states and learning rate in each layer), which greatly affect the performance of speech processing applications. To reach optimal p…