Woo Hyun Kang

Woo Hyun Kang, Jahangir Alam, Abderrahim Fathan

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in numerous tasks including speaker verification, language identification and anti-spoofing, their performance is limited when it comes to mismatched conditions due to the variability within them unrelated to the main task. In order to alleviate this problem, we propose a novel training strategy that regularizes the embedding network to have minimum information about the nuisance attributes. To achieve this, our proposed method directly incorporates the information bottleneck scheme into the training process, where the mutual information is estimated using the main task classifier and an auxiliary normalizing flow network. The proposed method was evaluated on different speech processing tasks and showed improvement over the standard training strategy in all experimentation.

Hyeongju Kim, Woo Hyun Kang, Hyeonseung Lee et al.

Photoplethysmogram (PPG) signal-based blood pressure (BP) estimation is a promising candidate for modern BP measurements, as PPG signals can be easily obtained from wearable devices in a non-invasive manner, allowing quick BP measurement. However, the performance of existing machine learning-based BP measuring methods still fall behind some BP measurement guidelines and most of them provide only point estimates of systolic blood pressure (SBP) and diastolic blood pressure (DBP). In this paper, we present a cutting-edge method which is capable of continuously monitoring BP from the PPG signal and satisfies healthcare criteria such as the Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS) standards. Furthermore, the proposed method provides the reliability of the predicted BP by estimating its uncertainty to help diagnose medical condition based on the model prediction. Experiments on the MIMIC II database verify the state-of-the-art performance of the proposed method under several metrics and its ability to accurately represent uncertainty in prediction.

Sung Hwan Mun, Woo Hyun Kang, Min Hyun Han et al.

In this paper, we propose a simple but powerful unsupervised learning method for speaker recognition, namely Contrastive Equilibrium Learning (CEL), which increases the uncertainty on nuisance factors latent in the embeddings by employing the uniformity loss. Also, to preserve speaker discriminability, a contrastive similarity loss function is used together. Experimental results showed that the proposed CEL significantly outperforms the state-of-the-art unsupervised speaker verification systems and the best performing model achieved 8.01% and 4.01% EER on VoxCeleb1 and VOiCES evaluation sets, respectively. On top of that, the performance of the supervised speaker embedding networks trained with initial parameters pre-trained via CEL showed better performance than those trained with randomly initialized parameters.

Sung Hwan Mun, Woo Hyun Kang, Min Hyun Han et al.

This paper describes our submission to Task 1 of the Short-duration Speaker Verification (SdSV) challenge 2020. Task 1 is a text-dependent speaker verification task, where both the speaker and phrase are required to be verified. The submitted systems were composed of TDNN-based and ResNet-based front-end architectures, in which the frame-level features were aggregated with various pooling methods (e.g., statistical, self-attentive, ghostVLAD pooling). Although the conventional pooling methods provide embeddings with a sufficient amount of speaker-dependent information, our experiments show that these embeddings often lack phrase-dependent information. To mitigate this problem, we propose a new pooling and score compensation methods that leverage a CTC-based automatic speech recognition (ASR) model for taking the lexical content into account. Both methods showed improvement over the conventional techniques, and the best performance was achieved by fusing all the experimented systems, which showed 0.0785% MinDCF and 2.23% EER on the challenge's evaluation subset.

Woo Hyun Kang, Sung Hwan Mun, Min Hyun Han et al.

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based methods are known to suffer from severe performance degradation when dealing with speech samples with different conditions (e.g., recording devices, emotional states). In this paper, we propose a novel fully supervised training method for extracting a speaker embedding vector disentangled from the variability caused by the nuisance attributes. The proposed framework was compared with the conventional deep learning-based embedding methods using the RSR2015 and VoxCeleb1 dataset. Experimental results show that the proposed approach can extract speaker embeddings robust to channel and emotional variability.

Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang et al.

For multi-channel speech recognition, speech enhancement techniques such as denoising or dereverberation are conventionally applied as a front-end processor. Deep learning-based front-ends using such techniques require aligned clean and noisy speech pairs which are generally obtained via data simulation. Recently, several joint optimization techniques have been proposed to train the front-end without parallel data within an end-to-end automatic speech recognition (ASR) scheme. However, the ASR objective is sub-optimal and insufficient for fully training the front-end, which still leaves room for improvement. In this paper, we propose a novel approach which incorporates flow-based density estimation for the robust front-end using non-parallel clean and noisy speech. Experimental results on the CHiME-4 dataset show that the proposed method outperforms the conventional techniques where the front-end is trained only with ASR objective.

Hyeonseung Lee, Woo Hyun Kang, Sung Jun Cheon et al.

Recently, attention-based encoder-decoder (AED) models have shown state-of-the-art performance in automatic speech recognition (ASR). As the original AED models with global attentions are not capable of online inference, various online attention schemes have been developed to reduce ASR latency for better user experience. However, a common limitation of the conventional softmax-based online attention approaches is that they introduce an additional hyperparameter related to the length of the attention window, requiring multiple trials of model training for tuning the hyperparameter. In order to deal with this problem, we propose a novel softmax-free attention method and its modified formulation for online attention, which does not need any additional hyperparameter at the training phase. Through a number of ASR experiments, we demonstrate the tradeoff between the latency and performance of the proposed online attention technique can be controlled by merely adjusting a threshold at the test phase. Furthermore, the proposed methods showed competitive performance to the conventional global and online attentions in terms of word-error-rates (WERs).

Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang et al.

Flow-based generative models are composed of invertible transformations between two random variables of the same dimension. Therefore, flow-based models cannot be adequately trained if the dimension of the data distribution does not match that of the underlying target distribution. In this paper, we propose SoftFlow, a probabilistic framework for training normalizing flows on manifolds. To sidestep the dimension mismatch problem, SoftFlow estimates a conditional distribution of the perturbed input data instead of learning the data distribution directly. We experimentally show that SoftFlow can capture the innate structure of the manifold data and generate high-quality samples unlike the conventional flow-based models. Furthermore, we apply the proposed framework to 3D point clouds to alleviate the difficulty of forming thin structures for flow-based models. The proposed model for 3D point clouds, namely SoftPointFlow, can estimate the distribution of various shapes more accurately and achieves state-of-the-art performance in point cloud generation.

Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang et al.

In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teacher network or a number of flow steps making them memory-inefficient. In this paper, we propose a novel generative model called WaveNODE which exploits a continuous normalizing flow for speech synthesis. Unlike the conventional models, WaveNODE places no constraint on the function used for flow operation, thus allowing the usage of more flexible and complex functions. Moreover, WaveNODE can be optimized to maximize the likelihood without requiring any teacher network or auxiliary loss terms. We experimentally show that WaveNODE achieves comparable performance with fewer parameters compared to the conventional flow-based vocoders.

Won Ik Cho, Jeonghwa Cho, Woo Hyun Kang et al.

Analyzing how human beings resolve syntactic ambiguity has long been an issue of interest in the field of linguistics. It is, at the same time, one of the most challenging issues for spoken language understanding (SLU) systems as well. As syntactic ambiguity is intertwined with issues regarding prosody and semantics, the computational approach toward speech intention identification is expected to benefit from the observations of the human language processing mechanism. In this regard, we address the task with attentive recurrent neural networks that exploit acoustic and textual features simultaneously and reveal how the modalities interact with each other to derive sentence meaning. Utilizing a speech corpus recorded on Korean scripts of syntactically ambiguous utterances, we revealed that co-attention frameworks, namely multi-hop attention and cross-attention, show significantly superior performance in disambiguating speech intention. With further analysis, we demonstrate that the computational models reflect the internal relationship between auditory and linguistic processes.

Won Ik Cho, Sung Jun Cheon, Woo Hyun Kang et al.

For readability and disambiguation of the written text, appropriate word segmentation is recommended for documentation, and it also holds for the digitized texts. If the language is agglutinative while far from scriptio continua, for instance in the Korean language, the problem becomes more significant. However, some device users these days find it challenging to communicate via key stroking, not only for handicap but also for being unskilled. In this study, we propose a real-time assistive technology that utilizes an automatic word segmentation, designed for digital minorities who are not familiar with electronic typing. We propose a data-driven system trained upon a spoken Korean language corpus with various non-canonical expressions and dialects, guaranteeing the comprehension of contextual information. Through quantitative and qualitative comparison with other text processing toolkits, we show the reliability of the proposed system and its fit with colloquial and non-normalized texts, which fulfills the aim of supportive technology.

Won Ik Cho, Young Ki Moon, Woo Hyun Kang et al.

Intention identification is a core issue in dialog management. However, due to the non-canonicality of the spoken language, it is difficult to extract the content automatically from the conversation-style utterances. This is much more challenging for languages like Korean and Japanese since the agglutination between morphemes make it difficult for the machines to parse the sentence and understand the intention. To suggest a guideline for this problem, and to merge the issue flexibly with the neural paraphrasing systems introduced recently, we propose a structured annotation scheme for Korean question/commands and the resulting corpus which are widely applicable to the field of argument mining. The scheme and dataset are expected to help machines understand the intention of natural language and grasp the core meaning of conversation-style instructions.