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.
Recent works have shown that hierarchical models lead to significant improvement in human activity recognition, which can not only enhance descriptive capability, but also improve discriminative power. However, most existing methods exploit just one of the two advantages. In this paper, a new hierarchical spatio-temporal model (HSTM) is proposed to integrate feature learning into two-layer hierarchical...
In this paper we describe the 2016 BBN conversational telephone speech keyword spotting system; the culmination of four years of research and development under the IARPA Babel program. The system was constructed in response to the NIST Open Keyword Search (OpenKWS) evaluation of 2016. We present our technological breakthroughs in building top-performing keyword spotting processing systems for new...
This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding. We introduce Bidirectional Long Short Term Memory - Long Short Term Memory networks (BLSTM-LSTM) as the encoder-decoder model to fully utilize the power of deep learning. In the sequence labelling task, the input and output sequences are aligned word by word, while the...
Automatic drum transcription methods aim at extracting a symbolic representation of notes played by a drum kit in audio recordings. For automatic music analysis, this task is of particular interest as such a transcript can be used to extract high level information about the piece, e.g., tempo, downbeat positions, meter, and genre cues. In this work, an approach to transcribe drums from polyphonic...
Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 video-level labels. We examine fully connected Deep Neural Networks (DNNs), AlexNet [1], VGG [2], Inception [3], and ResNet [4]. We investigate varying the...
Audio-visual speech recognition is a promising approach to tackling the problem of reduced recognition rates under adverse acoustic conditions. However, finding an optimal mechanism for combining multi-modal information remains a challenging task. Various methods are applicable for integrating acoustic and visual information in Gaussian-mixture-model-based speech recognition, e.g., via dynamic stream...
In this paper, a blind bandwidth extension algorithm for music signals has been proposed. This method applies the K-means algorithm to firstly cluster audio data in the feature space, and constructs multiple envelope predictors for each cluster accordingly using Support Vector Regression (SVR). A set of well-established audio features for Music Information Retrieval (MIR) has been used to characterize...
Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition systems correspond to context-dependent tied states or senones. The present work addresses some limitations of GMM-HMM senone alignments for DNN training. We hypothesize...
It has been shown that sequence-discriminative training can improve the performance for large vocabulary continuous speech recognition. Our main contribution is a novel method for reducing the computation time of any sort of sequence training while only slightly decreasing the overall performance. The method allows to parallelize the forward propagation through the network, the loss and loss gradient...
A multi-stream framework with deep neural network (DNN) classifiers is applied to improve automatic speech recognition (ASR) in environments with different reverberation characteristics. We propose a room parameter estimation model to establish a reliable combination strategy which performs on either DNN posterior probabilities or word lattices. The model is implemented by training a multilayer perceptron...
We describe and analyze a simple and effective algorithm for sequence segmentation applied to speech processing tasks. We propose a neural architecture that is composed of two modules trained jointly: a recurrent neural network (RNN) module and a structured prediction model. The RNN outputs are considered as feature functions to the structured model. The overall model is trained with a structured...
The problem of inferring the hidden state of individual nodes in social/sensor networks in which node activities affect their neighbors is growing in importance. We present an undirected generative model, a type of probabilistic model that has so far not been used for modeling latent variables influenced by neighbors in a network. We also propose an efficient inference method based on variational...
In this paper, we present an expressive visual text to speech system (VTTS) based on a deep neural network (DNN). Given an input text sentence and a set of expression tags, the VTTS is able to produce not only the audio speech, but also the accompanying facial movements. The expressions can either be one of the expressions in the training corpus or a blend of expressions from the training corpus....
End-to-end (E2E) systems have achieved competitive results compared to conventional hybrid hidden Markov model (HMM)-deep neural network based automatic speech recognition (ASR) systems. Such E2E systems are attractive due to the lack of dependence on alignments between input acoustic and output grapheme or HMM state sequence during training. This paper explores the design of an ASR-free end-to-end...
This paper presents a new hybrid approach for polyphonic Sound Event Detection (SED) which incorporates a temporal structure modeling technique based on a hidden Markov model (HMM) with a frame-by-frame detection method based on a bidirectional long short-term memory (BLSTM) recurrent neural network (RNN). The proposed BLSTM-HMM hybrid system makes it possible to model sound event-dependent temporal...
Recent work on Acoustic Unit Discovery (AUD) has led to the development of a non-parametric Bayesian phone-loop model where the prior over the probability of the phone-like units is assumed to be sampled from a Dirichlet Process (DP). In this work, we propose to improve this model by incorporating a Hierarchical Pitman-Yor based bigram Language Model on top of the units' transitions. This new model...
A novel speaker segmentation approach based on deep neural network is proposed and investigated. This approach uses deep speaker vectors (d-vectors) to represent speaker characteristics and to find speaker change points. The d-vector is a kind of frame-level speaker discriminative feature, whose discriminative training process corresponds to the goal of discriminating a speaker change point from a...
It is well known that, when noisy speech is transcribed using automatic speech recognition (ASR) systems trained on clean data, a highly degraded recognition performance is obtained. The problemgets further aggravatedwhen the targeted group happens to be child speakers. For children's speech, the acoustic correlates such as pitch and formant frequency vary significantly with age. This makes the recognition...
Deep neural networks (DNN) have achieved significant success in the field of speech recognition. One of the main advantages of the DNN is automatic feature extraction without human intervention. Therefore, we incorporate a pseudo-filterbank layer to the bottom of DNN and train the whole filterbank layer and the following networks jointly, while most systems take pre-defined mel-scale filterbanks as...
Model-based approaches to Speaker Verification (SV), such as Joint Factor Analysis (JFA), i-vector and relevance Maximum-a-Posteriori (MAP), have shown to provide state-of-the-art performance for text-dependent systems with fixed phrases. The performance of i-vector and JFA models has been further enhanced by estimating posteriors from Deep Neural Network (DNN) instead of Gaussian Mixture Model (GMM)...
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.