The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Adapting acoustic models to speakers have shown to greatly improve performance for many tasks. Among the adaptation approaches, exploiting auxiliary features characterizing speakers or environments has received great attention because they allow rapid adaptation, i.e. adaptation with limited amount of speech data such as a single utterance. However, the auxiliary features are usually computed in batch...
Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping between variable-length input and output sequences in one step using a purely data-driven method. The attention model has often been shown to improve the performance...
In bioacoustics, automatic animal voice detection and recognition from audio recordings is an emerging topic for animal preservation. Our research focuses on bird bioacoustics, where the goal is to segment bird syllables from the recording and predict the bird species for the syllables. Traditional methods for this task addresses the segmentation and species prediction separately, leading to propagated...
This paper presents a framework for modeling neural decoding using electromyogram (EMG) and electrocorticogram (ECoG) signals to interpret human intent and control prosthetic arms. Specifically, the method of this paper employs Markov Decision Processes (MDP) for neural decoding, parameterizing the policy using an artificial neural network. The system is trained using a modification of the Dataset...
Bidirectional long short-term memory (BLSTM) recurrent neural networks are powerful acoustic models in terms of recognition accuracy. When BLSTM acoustic models are used in decoding, the speech decoder needs to wait until the end of a whole sentence is reached, such that forward-propagation in the backward direction can then be performed. The nature of BLSTM acoustic models makes them inappropriate...
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent...
Time-based Spiking Neural Network (SNN) has recently received increased attentions in neuromorphic computing system designs due to more bio-plausibility and better energy-efficiency. However, unleashing its potentials in realistic cognitive applications is facing significant challenges such as inefficient information representations and impractical learnings. In this work, we aim for exploring a practical...
The majority of successful automatic speech recognition (ASR) systems utilize a probabilistic modeling of the speech signal via hidden Markov models (HMMs). In a standard HMM model, state duration probabilities decrease exponentially with time, which fails to satisfactorily describe the temporal structure of speech. Incorporating explicit state durational probability distribution functions (pdf) into...
Spatial separation of suspended particles based on contrast in their physical or chemical properties forms the basis of various biological assays performed on lab-on-a-chip devices. To electronically acquire this information, we have recently introduced a microfluidic sensing platform, called Microfluidic CODES, which combines the resistive pulse sensing with the code division multiple access in multiplexing...
Automatic speech recognition (ASR) in noisy environments remains a challenging goal. Recently, the idea of estimating the uncertainty about the features obtained after speech enhancement and propagating it to dynamically adapt deep neural network (DNN) based acoustic models has raised some interest. However, the results in the literature were reported on simulated noisy datasets for a limited variety...
We present a simplified and novel fully convolutional neural network (CNN) architecture for semantic pixel-wise segmentation named as SCNet. Different from current CNN pipelines, proposed network uses only convolution layers with no pooling layer. The key objective of this model is to offer a more simplified CNN model with equal benchmark performance and results. It is an encoder-decoder based fully...
Handwritten word recognition is a tough task, mixing image and natural language processing. Recently new recurrent neural networks with LSTM cells allowed significant improvements in this field. These networks are generally coupled with lexical and linguistic knowledge in order to correct character misrecognitions, namely using a lexicon driven decoding. Yet the high performances of LSTM networks...
Error Correcting Output Coding (ECOC) is a multi-class classification technique in which multiple binary classifiers are trained according to a preset code matrix such that each one learns a separate dichotomy of the classes. While ECOC is one of the best solutions for multi-class problems, one issue which makes it suboptimal is that the training of the base classifiers is done independently of the...
In this paper, we propose a novel patch-based face hallucination method that consists of two patch-based sparse autoencoder (SAE) networks and a deep fully connected network (namely traversal network). The SAE networks are used to capture the intrinsic features of low-resolution (LR) images and high-resolution (HR) images in the hidden layers, while the traversal network is used to map features from...
In this paper, we present a novel image codec by leveraging sparse representation strategy for geometric pattern encoding. Specifically, we propose a Multiple Learned Geometric Dictionaries (MLGD) solution to explore various texture patterns of images, and use different dictionaries to encode homogenous smooth components and heterogeneous directional components. Profiting from model proficiency, our...
In this paper, we introduce a multimodal speech recognition scenario, in which an image provides contextual information for a spoken caption to be decoded. We investigate a lattice rescoring algorithm that integrates information from the image at two different points: the image is used to augment the language model with the most likely words, and to rescore the top hypotheses using a word-level RNN...
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothing based evaluation approach is employed to measure keyword spotting performance...
Headline generation for spoken content is important since spoken content is difficult to be shown on the screen and browsed by the user. It is a special type of abstractive summarization, for which the summaries are generated word by word from scratch without using any part of the original content. Many deep learning approaches for headline generation from text document have been proposed recently,...
Large-scale monitoring of the child language environment through measuring the amount of speech directed to the child by other children and adults during a vocal communication is an important task. Using the audio extracted from a recording unit worn by a child within a childcare center, at each point in time our proposed diarization system can determine the content of the child's language environment,...
In this paper we propose a framework for building a full-fledged acoustic unit recognizer in a zero resource setting, i.e., without any provided labels. For that, we combine an iterative Dirichlet process Gaussian mixture model (DPGMM) clustering framework with a standard pipeline for supervised GMM-HMM acoustic model (AM) and n-gram language model (LM) training, enhanced by a scheme for iterative...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.