This work explores the use of various Deep Neural Network (DNN) architectures for an end-to-end language identification (LID) task. The approach has been proven to significantly improve the state-of-art in many domains include speech recognition, computer vision and genomics. As an end-to-end system, deep learning removes the burden of hand crafting the feature extraction is conventional approach in LID. This versatility is achieved by training a very deep network to learn distributed representations of speech features with multiple levels of abstraction. In this paper, we show that an end-to-end deep learning system can be used to recognize language from speech utterances with various lengths. Our results show that a combination of three deep architectures: feed-forward network, convolutional network and recurrent network can achieve the best performance compared to other network designs. Additionally, we compare our network performance to state-of-the-art BNF-based i-vector system on NIST 2015 Language Recognition Evaluation corpus. Key to our approach is that we effectively address computational and regularization issues into the network structure to build deeper architecture compare to any previous DNN approaches to language recognition task.

Single-cell transcriptomics offers a tool to study the diversity of cell phenotypes through snapshots of the abundance of mRNA in individual cells. Often there is additional information available besides the single-cell gene expression counts, such as bulk transcriptome data from the same tissue, or quantification of surface protein levels from the same cells. In this study, we propose models based on the Bayesian deep learning approach, where protein quantification, available as CITE-seq counts, from the same cells is used to constrain the learning process, thus forming a SemI-SUpervised generative Autoencoder (SISUA) model. The generative model is based on the deep variational autoencoder (VAE) neural network architecture.

No abstract

The series of language recognition evaluations (LRE's) conducted by the National Institute of Standards and Technology (NIST) have been one of the driving forces in advancing spoken language recognition technology. This paper presents a shared view of five institutions resulting from our collaboration toward LRE 2015 submissions under the names of I2R, Fan-tastic4, and SingaMS. Among others, LRE'15 emphasizes on language detection in the context of closely related languages, which is different from previous LRE's. From the perspective of language recognition system design, we have witnessed a major paradigm shift in adopting deep neural network (DNN) for both feature extraction and classifier. In particular, deep bottleneck features (DBF) have a significant advantage in replacing the shifted-delta-cepstral (SDC) which has been the only option in the past. We foresee deep learning is going to serve as a major driving force in advancing spoken language recognition system in the coming years. Index Terms: spoken language recognition, evaluation 2. Baseline, data and performance metric 2.1. BaselineWe started off with the baseline system as shown in Fig. 1. Speech utterances are first parameterized as sequences of shifted delta cepstral (SDC) feature vectors [7,8]. They are then represented as i-vectors which compress the variable-length sequences along the time axis and project the resulting vectors to the low-dimensional total variability space. Having its root in

Bottleneck features (BNFs) generated with a deep neural network (DNN) have proven to boost spoken language recognition accuracy over basic spectral features significantly. However, BNFs are commonly extracted using language-dependent tied-context phone states as learning targets. Moreover, BNFs are less phonetically expressive than the output layer in a DNN, which is usually not used as a speech feature because of its very high dimensionality hindering further post-processing. In this article, we put forth a novel deep learning framework to overcome all of the above issues and evaluate it on the 2017 NIST Language Recognition Evaluation (LRE) challenge. We use manner and place of articulation as speech attributes, which lead to low-dimensional "universal" phonetic features that can be defined across all spoken languages. To model the asynchronous nature of the speech attributes while capturing their intrinsic relationships in a given speech segment, we introduce a new training scheme for deep architectures based on a Maximal Figure of Merit (MFoM) objective. MFoM introduces non-differentiable metrics into the backpropagation-based approach, which is elegantly solved in the proposed framework. The experimental evidence collected on the recent NIST LRE 2017 challenge demonstrates the effectiveness of our solution. In fact, the performance of speech language recognition (SLR) systems based on spectral features is improved for more than 5% absolute Cavg. Finally, the F1 metric can be brought from 77.6% up to 78.1% by combining the conventional baseline phonetic BNFs with the proposed articulatory attribute features.