Remarkable gains in deep learning usually rely on tremendous supervised data. Ensuring the modality diversity for one object in training set is critical for the generalization of cutting-edge deep models, but it burdens human with heavy manual labor on data collection and annotation. In addition, some rare or unexpected modalities are new for the current model, causing reduced performance under such emerging modalities. Inspired by the achievements in speech recognition, psychology and behavioristics, we present a practical solution, self-reinforcing unsupervised matching (SUM), to annotate the images with 2D structure-preserving property in an emerging modality by cross-modality matching. This approach requires no any supervision in emerging modality and only one template in seen modality, providing a possible route towards continual learning.
How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/YouTube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of faces and speech in Internet videos, without the need to model attributes explicitly. We evaluate and numerically quantify how--and in what manner--our Speech2Face reconstructions, obtained directly from audio, resemble the true face images of the speakers.
Many studies have been undertaken by using machine learning techniques, including neural networks, to predict stock returns. Recently, a method known as deep learning, which achieves high performance mainly in image recognition and speech recognition, has attracted attention in the machine learning field. This paper implements deep learning to predict one-month-ahead stock returns in the cross-section in the Japanese stock market and investigates the performance of the method. Our results show that deep neural networks generally outperform shallow neural networks, and the best networks also outperform representative machine learning models. These results indicate that deep learning shows promise as a skillful machine learning method to predict stock returns in the cross-section.
This paper addresses the observed performance gap between automatic speech recognition (ASR) systems based on Long Short Term Memory (LSTM) neural networks trained with the connectionist temporal classification (CTC) loss function and systems based on hybrid Deep Neural Networks (DNNs) trained with the cross entropy (CE) loss function on domains with limited data. We step through a number of experiments that show incremental improvements on a baseline EESEN toolkit based LSTM-CTC ASR system trained on the Librispeech 100hr (train-clean-100) corpus. Our results show that with effective combination of data augmentation and regularization, a LSTM-CTC based system can exceed the performance of a strong Kaldi based baseline trained on the same data.
Word discovery is the task of extracting words from unsegmented text. In this paper we examine to what extent neural networks can be applied to this task in a realistic unwritten language scenario, where only small corpora and limited annotations are available. We investigate two scenarios: one with no supervision and another with limited supervision with access to the most frequent words. Obtained results show that it is possible to retrieve at least 27% of the gold standard vocabulary by training an encoder-decoder neural machine translation system with only 5,157 sentences. This result is close to those obtained with a task-specific Bayesian nonparametric model. Moreover, our approach has the advantage of generating translation alignments, which could be used to create a bilingual lexicon. As a future perspective, this approach is also well suited to work directly from speech.
Keyword spotting (KWS) constitutes a major component of human-technology interfaces. Maximizing the detection accuracy at a low false alarm (FA) rate, while minimizing the footprint size, latency and complexity are the goals for KWS. Towards achieving them, we study Convolutional Recurrent Neural Networks (CRNNs). Inspired by large-scale state-of-the-art speech recognition systems, we combine the strengths of convolutional layers and recurrent layers to exploit local structure and long-range context. We analyze the effect of architecture parameters, and propose training strategies to improve performance. With only ~230k parameters, our CRNN model yields acceptably low latency, and achieves 97.71% accuracy at 0.5 FA/hour for 5 dB signal-to-noise ratio.
Language Identification, being an important aspect of Automatic Speaker Recognition has had many changes and new approaches to ameliorate performance over the last decade. We compare the performance of using audio spectrum in the log scale and using Polyphonic sound sequences from raw audio samples to train the neural network and to classify speech as either English or Spanish. To achieve this, we use the novel approach of using a Convolutional Recurrent Neural Network using Long Short Term Memory (LSTM) or a Gated Recurrent Unit (GRU) for forward propagation of the neural network. Our hypothesis is that the performance of using polyphonic sound sequence as features and both LSTM and GRU as the gating mechanisms for the neural network outperform the traditional MFCC features using a unidirectional Deep Neural Network.
Deep learning is a branch of artificial intelligence employing deep neural network architectures that has significantly advanced the state-of-the-art in computer vision, speech recognition, natural language processing and other domains. In November 2015, Google released $\textit{TensorFlow}$, an open source deep learning software library for defining, training and deploying machine learning models. In this paper, we review TensorFlow and put it in context of modern deep learning concepts and software. We discuss its basic computational paradigms and distributed execution model, its programming interface as well as accompanying visualization toolkits. We then compare TensorFlow to alternative libraries such as Theano, Torch or Caffe on a qualitative as well as quantitative basis and finally comment on observed use-cases of TensorFlow in academia and industry.
Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen words. We propose to improve word embeddings by incorporating morphological information, capturing shared sub-word features. Unlike previous work that constructs word embeddings directly from morphemes, we combine morphological and distributional information in a unified probabilistic framework, in which the word embedding is a latent variable. The morphological information provides a prior distribution on the latent word embeddings, which in turn condition a likelihood function over an observed corpus. This approach yields improvements on intrinsic word similarity evaluations, and also in the downstream task of part-of-speech tagging.
The paper describes the Egyptian Arabic-to-English statistical machine translation (SMT) system that the QCRI-Columbia-NYUAD (QCN) group submitted to the NIST OpenMT'2015 competition. The competition focused on informal dialectal Arabic, as used in SMS, chat, and speech. Thus, our efforts focused on processing and standardizing Arabic, e.g., using tools such as 3arrib and MADAMIRA. We further trained a phrase-based SMT system using state-of-the-art features and components such as operation sequence model, class-based language model, sparse features, neural network joint model, genre-based hierarchically-interpolated language model, unsupervised transliteration mining, phrase-table merging, and hypothesis combination. Our system ranked second on all three genres.
Add to Chrome
Add to Firefox