Recent studies have been revisiting whole words as the basic modelling unit in speech recognition and query applications, instead of phonetic units. Such whole-word segmental systems rely on a function that maps a variable-length speech segment to a vector in a fixed-dimensional space; the resulting acoustic word embeddings need to allow for accurate discrimination between different word types, directly in the embedding space. We compare several old and new approaches in a word discrimination task. Our best approach uses side information in the form of known word pairs to train a Siamese convolutional neural network (CNN): a pair of tied networks that take two speech segments as input and produce their embeddings, trained with a hinge loss that separates same-word pairs and different-word pairs by some margin. A word classifier CNN performs similarly, but requires much stronger supervision. Both types of CNNs yield large improvements over the best previously published results on the word discrimination task.Index Terms-Acoustic word embeddings, segmental acoustic models, fixed-dimensional representations, query-by-example search.

It has been previously shown that, when both acoustic and articulatory training data are available, it is possible to improve phonetic recognition accuracy by learning acoustic features from this multiview data with canonical correlation analysis (CCA). In contrast with previous work based on linear or kernel CCA, we use the recently proposed deep CCA, where the functional form of the feature mapping is a deep neural network. We apply the approach on a speakerindependent phonetic recognition task using data from the University of Wisconsin X-ray Microbeam Database. Using a tandem-style recognizer on this task, deep CCA features improve over earlier multiview approaches as well as over articulatory inversion and typical neural network-based tandem features. We also present a new stochastic training approach for deep CCA, which produces both faster training and better-performing features.Index Terms-multi-view learning, neural networks, deep canonical correlation analysis, XRMB, articulatory measurements INTRODUCTIONModern speech recognizers often use deep neural networks (DNNs) trained to predict the posterior probabilities of phonetic states [1]. In the two most common approaches, either (1) the DNN outputs are scaled by the state priors and used as an observation model in a hidden Markov model (HMM)-based recognizer (the hybrid approach [2]) or (2) the outputs of some layer of the network (possibly a narrow "bottleneck" layer or the final layer) are post-processed and used as acoustic features in an HMM system with a Gaussian mixture model (GMM) observation distribution (the tandem approach [3]). Working within the tandem approach, we investigate whether we can learn better DNN-based acoustic features via unsupervised learning using an external set of unlabeled multi-view data, in our case simultaneously recorded audio and articulatory measurements.The idea of feature learning using multi-view data has been explored previously using canonical correlation analysis (CCA) [4] and its nonlinear extension kernel CCA (KCCA) [5,6]. Here we propose to use the recently devloped deep CCA (DCCA) approach, which differs from linear/kernel CCA in that the feature mapping is implemented with a DNN rather than a linear/kernel function. Considering the earlier successes of CCA/KCCA, and the general success of DNNs for speech tasks, it is a natural question whether multi-view feature learning can benefit from the more flexible functional form of a DNN. We investigate this question, using data from the University of Wisconsin X-ray Microbeam Database (XRMB) [7], on speakerindependent phonetic recognition in a setting where no articulatory data is available for the recognizer training speakers. We find that DCCA indeed improves over previous CCA-based features, as well

Word embeddings have been found useful for many NLP tasks, including part-of-speech tagging, named entity recognition, and parsing. Adding multilingual context when learning embeddings can improve their quality, for example via canonical correlation analysis (CCA) on embeddings from two languages. In this paper, we extend this idea to learn deep non-linear transformations of word embeddings of the two languages, using the recently proposed deep canonical correlation analysis. The resulting embeddings, when evaluated on multiple word and bigram similarity tasks, consistently improve over monolingual embeddings and over embeddings transformed with linear CCA.

We study the problem of acoustic feature learning in the setting where we have access to another (non-acoustic) modality for feature learning but not at test time. We use deep variational canonical correlation analysis (VCCA), a recently proposed deep generative method for multi-view representation learning. We also extend VCCA with improved latent variable priors and with adversarial learning. Compared to other techniques for multi-view feature learning, VCCA's advantages include an intuitive latent variable interpretation and a variational lower bound objective that can be trained end-to-end efficiently. We compare VCCA and its extensions with previous feature learning methods on the University of Wisconsin X-ray Microbeam Database, and show that VCCA-based feature learning improves over previous methods for speaker-independent phonetic recognition.

Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learning in several domains. However, stochastic optimization of the deep CCA objective is not straightforward, because it does not decouple over training examples. Previous optimizers for deep CCA are either batch-based algorithms or stochastic optimization using large minibatches, which can have high memory consumption. In this paper, we tackle the problem of stochastic optimization for deep CCA with small minibatches, based on an iterative solution to the CCA objective, and show that we can achieve as good performance as previous optimizers and thus alleviate the memory requirement.

Anaplastic thyroid carcinoma (ATC) responds for the majority of death of thyroid carcinoma and often causes chemotherapy resistance. We investigated the influence of circEIF6 (Hsa_circ_0060060) on the cisplatin-sensitivity in papillary thyroid carcinoma (PTC) and ATC cells, and explored its regulation to downstream molecules miR-144-3p and Transforming Growth Factor α (TGF-α). Differentially expressed circRNAs in PTC were analyzed using the GSE93522 data downloaded. Expressions of circEIF6, miR-144-3p, TGF-α, autophagy-related proteins and apoptosis-related proteins were determined using qRT-PCR or western blot. RNA pull-down assay and dual luciferase report assay were applied to reveal the target relationships. Autophagy marker LC3 and cell proliferation marker ki67 were evaluated by immunofluorescence and immunohistochemistry. Cell viability was evaluated with MTT assay and cell apoptosis was assessed by flow cytometric analysis. CircEIF6, could promote autophagy induced by cisplatin, thus inhibiting cell apoptosis and enhancing the resistance of PTC and ATC cells to cisplatin. Has-miR-144-3p was the target of circEIF6 and was regulated by circEIF6. Besides, circEIF6 promoted autophagy by regulating miR-144-3p/TGF-α axis, enhancing the cisplatin-resistance in PTC and ATC cells. CircEIF6 promoted tumor growth by regulating miR-144-3p/TGF-α and circEIF6 knock-down enhanced cisplatin sensitivity in vivo. CircEIF6 could provide a target for therapy of cisplatin-resistance in thyroid carcinoma.

No abstract

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The pre-trained networks can then be fine-tuned on a smaller amount of supervised data for speech recognition. Experiments with this approach on the LibriSpeech and Wall Street Journal corpora show promising results. We find that the main factors that lead to speech recognition improvements are: masking segments of sufficient width in both time and frequency, pre-training on a much larger amount of unlabeled data than the labeled data, and domain adaptation when the unlabeled and labeled data come from different domains. The gain from pre-training is additive to that of supervised data augmentation.