检索结果-内蒙古大学图书馆

Sample drop detection for distant-speech recognition with asynchronous devices distributed in space

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Raissi, Tina Pascual, Santiago Omologo, Maurizio Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany Universitat Politècnica de Catalunya Barcelona Spain Center for Information and Communication Technology Fondazione Bruno Kessler Trento Italy

In many applications of multi-microphone multi-device processing, the synchronization among different input channels can be affected by the lack of a common clock and isolated drops of samples. In this work, we address the issue of sample drop detection in the context of a conversational speech scenario, recorded by a set of microphones distributed in space. The goal is to design a neural-based model that given a short window in the time domain, detects whether one or more devices have been subjected to a sample drop event. The candidate time windows are selected from a set of large time intervals, possibly including a sample drop, and by using a preprocessing step. The latter is based on the application of normalized cross-correlation between signals acquired by different devices. The architecture of the neural network relies on a CNN-LSTM encoder, followed by multi-head attention. The experiments are conducted using both artificial and real data. Our proposed approach obtained F1 score of 88% on an evaluation set extracted from the CHiME-5 corpus. A comparable performance was found in a larger set of experiments conducted on a set of multi-channel artificial scenes. Copyright © 2019, The Authors. All rights reserved.

关键词： Speech recognition

Automatic Semantic Segmentation of the Lumbar Spine: Clinical Applicability in a Multi-parametric and Multi-centre Study on Magnetic Resonance Images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sáenz-Gamboa, Jhon Jairo Domenech, Julio Alonso-Manjarrés, Antonio Gómez, Jon A. de la Iglesia-Vayá, Maria Av. de Catalunya 21 València46020 Spain Orthopedic Surgery Department Hospital Arnau de Vilanova Carrer de San Clemente s/n València46015 Spain Radiology Department Hospital Arnau de Vilanova Carrer de San Clemente s/n València46015 Spain Pattern Recognition and Human Language Technology Research Center Universitat Politècnica de València Camí de Vera s/n València46022 Spain Regional Ministry of Universal Health and Public Health in Valencia Carrer de Misser Mascó 31 València46010 Spain

One of the major difficulties in medical image segmentation is the high variability of these images, which is caused by their origin (multi-centre), the acquisition protocols (multi-parametric), as well as the variability of human anatomy, the severity of the illness, the effect of age and gender, among others. The problem addressed in this work is the automatic semantic segmentation of lumbar spine Magnetic Resonance images using convolutional neural networks. The purpose is to assign a class label to each pixel of an image. Classes were defined by radiologists and correspond to different structural elements like vertebrae, intervertebral discs, nerves, blood vessels, and other tissues. The proposed network topologies are variants of the U-Net architecture. Several complementary blocks were used to define the variants: Three types of convolutional blocks, spatial attention models, deep supervision and multilevel feature extractor. This document describes the topologies and analyses the results of the neural network designs that obtained the most accurate segmentations. Several of the proposed designs outperform the standard U-Net used as baseline, especially when used in ensembles where the output of multiple neural networks is combined according to different *** Codes 92B20, 92C50, 68T07, 68T45, 68U10, 92B10 © 2021, CC BY.

关键词： Convolution

Optimizing Energies for Pose-Invariant Face recognition

学校读者我要写书评

暂无评论

Optimizing Energies for Pose-Invariant Face Recognition

International Conference on pattern recognition

作者： Harald Hanselmann Hermann Ney Human Language Technology and Pattern Recognition Group RWTH Aachen University Aachen Germany

One of the most difficult challenges in face recognition is the large variation in pose. One approach to handle this problem is to use a 2D-Warping algorithm in a nearest-neighbor classifier. The 2D-Warping algorithm optimizes an energy function that captures the cost of matching pixels between two images while respecting the 2D dependencies defined by local pixel neighborhoods. Optimizing this energy function is an NP-complete problem and is therefore approached with algorithms that aim to approximate the optimal solution. In this paper we compare two algorithms that do this without discarding any 2D dependencies and we study the effect of the quality of the approximate solutions on the classification performance. Additionally, we propose a new algorithm that is capable of finding better solutions and obtaining better energies than the other methods. The experimental evaluation on the CMU-MultiPIE database shows that the proposed algorithm also achieves state-of-the-art recognition accuracies.

关键词： Two dimensional displays Face recognition Approximation algorithms Dynamic programming Face Heuristic algorithms Message passing

Speaker adapted beamforming for multi-channel automatic speech recognition

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Menne, Tobias Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany

This paper presents, in the context of multi-channel ASR, a method to adapt a mask based, statistically optimal beamforming approach to a speaker of interest. The beamforming vector of the statistically optimal beamformer is computed by utilizing speech and noise masks, which are estimated by a neural network. The proposed adaptation approach is based on the integration of the beamformer, which includes the mask estimation network, and the acoustic model of the ASR system. This allows for the propagation of the training error, from the acoustic modeling cost function, all the way through the beamforming operation and through the mask estimation network. By using the results of a first pass recognition and by keeping all other parameters fixed, the mask estimation network can therefore be fine tuned by retraining. Utterances of a speaker of interest can thus be used in a two pass approach, to optimize the beamforming for the speech characteristics of that specific speaker. It is shown that this approach improves the ASR performance of a state-of-the-art multi-channel ASR system on the CHiME-4 data. Furthermore the effect of the adaptation on the estimated speech masks is discussed. Copyright © 2018, The Authors. All rights reserved.

关键词： Cost functions

ACOUSTIC MODELING OF SPEECH WAVEFORM BASED ON MULTI-RESOLUTION, NEURAL NETWORK SIGNAL PROCESSING

学校读者我要写书评

暂无评论

ACOUSTIC MODELING OF SPEECH WAVEFORM BASED ON MULTI-RESOLUTI...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Zoltán Tüske Ralf Schlüter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52056 Aachen Germany

ISBN: (纸本)9781538646595

Recently, several papers have demonstrated that neural networks (NN) are able to perform the feature extraction as part of the acoustic model. Motivated by the Gammatone feature extraction pipeline, in this paper we extend the waveform based NN model by a second level of time-convolutional element. The proposed extension generalizes the envelope extraction block, and allows the model to learn multi-resolutional representations. Automatic speech recognition (ASR) experiments show significant word error rate reduction over our previous best acoustic model trained in the signal domain directly. Although we use only 250 hours of speech, the data-driven NN based speech signal processing performs nearly equally to traditional handcrafted feature extractors. In additional experiments, we also test segment-level feature normalization techniques on NN derived features, which improve the results further. However, the porting of speech representations derived by a feed-forward NN to a LSTM back-end model indicates much less robustness of the NN front-end compared to the standard feature extractors. Analysis of the weights in the proposed new layer reveals that the NN prefers both multi-resolution and modulation spectrum representations.

关键词： ASR neural network time-signal waveform modulation spectrum feature representation modulation spectra waveforms time signal Speech recognition Neural network aquifer storage and recovery Feature extraction Speech signal processing Multi-resolution Acoustic models

Sign language Gesture Classification Using Neural Networks 4

学校读者我要写书评

暂无评论

Sign Language Gesture Classification Using Neural Networks

4th International Conference on Advances in Speech and language Technologies for Iberian languages, IberSPEECH 2018

作者： Parcheta, Zuzanna Martínez-Hinarejos, Carlos-D. Sciling S.L. Carrer del Riu 321 Pinedo 46012 Spain Pattern Recognition and Human Language Technology Research Center Universitat Politècnica de València Camino de Vera s/n 46022 Spain

Recent studies have demonstrated the power of neural networks for different fields of artificial intelligence. In most fields, such as machine translation or speech recognition, neural networks outperform previously used methods (Hidden Markov Models with Gaussian Mixtures, Statistical Machine Translation, etc.). In this paper, the efficiency of the LeNet convolutional neural network for isolated word sign language recognition is demonstrated. As a preprocessing step, we apply several techniques to obtain the same dimension for the input that contains gesture information. The performance of these preprocessing techniques on a Spanish Sign language dataset is evaluated. These approaches outperform previously obtained results based on Hidden Markov Models. © 4th International Conference, IberSPEECH 2018.

关键词： Gesture recognition

Prediction of LSTM-RNN Full Context States as a Subtask for N-Gram Feedforward language Models

学校读者我要写书评

暂无评论

Prediction of LSTM-RNN Full Context States as a Subtask for ...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Kazuki Irie Zhihong Lei Ralf Schlüter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University D-52056 Aachen Germany

ISBN: (纸本)9781538646595

Long short-term memory (LSTM) recurrent neural network language models compress the full context of variable lengths into a fixed size vector. In this work, we investigate the task of predicting the LSTM hidden representation of the full context from a truncated n-gram context as a subtask for training an n-gram feedforward language model. Since this approach is a form of knowledge distillation, we compare two methods. First, we investigate the standard transfer based on the Kullback-Leibler divergence of the output distribution of the feedforward model from that of the LSTM. Second, we minimize the mean squared error between the hidden state of the LSTM and that of the n-gram feedforward model. We carry out experiments on different subsets of the Switchboard speech recognition dataset for feedforward models with a short (5-gram) and a medium (10-gram) context length. We show that we get improvements in perplexity and word error rate of up to 8% and 4% relative for the medium model, while the improvements are only marginal for the short model.

关键词： language modeling neural networks knowledge distillation student-teacher speech recognition modelling languages Speech recognition FEEDFORWARD Neural network Error analysis

Unsupervised training for large vocabulary translation using sparse lexicon andword classes 15

学校读者我要写书评

暂无评论

Unsupervised training for large vocabulary translation using...

15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017

作者： Kim, Yunsu Schamper, Julian Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany

ISBN: (纸本)9781510838604

We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text or seed lexicon. First, we solve the memory bottleneck and enforce the sparsity with a simple thresholding scheme for the lexicon. Second, we initialize the lexicon training with word classes, which efficiently boosts the performance. Our methods produced promising results on two large-scale unsupervised translation tasks. © 2017 Association for Computational Linguistics.

关键词： Maximum principle

Towards two-dimensional sequence to sequence model in neural machine translation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Bahar, Parnia Brix, Christopher Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department Rwth Aachen University AachenD-52056 Germany

This work investigates an alternative model for neural machine translation (NMT) and proposes a novel architecture, where we employ a multi-dimensional long short-term memory (MDLSTM) for translation modeling. In the state-of-the-art methods, source and target sentences are treated as one-dimensional sequences over time, while we view translation as a two-dimensional (2D) mapping using an MDLSTM layer to define the correspondence between source and target words. We extend beyond the current sequence to sequence backbone NMT models to a 2D structure in which the source and target sentences are aligned with each other in a 2D grid. Our proposed topology shows consistent improvements over attention-based sequence to sequence model on two WMT 2017 tasks, German↔English. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural machine translation