检索结果-内蒙古大学图书馆

A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zeineldeen, Mohammad Zeyer, Albert Zhou, Wei Ng, Thomas Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52062 Aachen Germany AppTek GmbH Aachen52062 Germany

Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e.g. byte-pair encoding (BPE). The mapping from pronunciation to spelling is learned completely from data. In contrast to this, classical approaches to ASR employ secondary knowledge sources in the form of phoneme lists to define phonetic output labels and pronunciation lexica. In this work, we do a systematic comparison between grapheme- and phoneme-based output labels for an encoder-decoder-attention ASR model. We investigate the use of single phonemes as well as BPE-based phoneme groups as output labels of our model. To preserve a simplified and efficient decoder design, we also extend the phoneme set by auxiliary units to be able to distinguish homophones. Experiments performed on the Switchboard 300h and LibriSpeech benchmarks show that phoneme-based modeling is competitive to grapheme-based encoder-decoder-attention modeling. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech recognition

Investigation of large-margin softmax in neural language modeling

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Huo, Jingjing Gao, Yingbo Wang, Weiyue Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

To encourage intra-class compactness and inter-class separability among trainable feature vectors, large-margin softmax methods are developed and widely applied in the face recognition community. The introduction of the large-margin concept into the softmax is reported to have good properties such as enhanced discriminative power, less overfitting and well-defined geometric intuitions. Nowadays, language modeling is commonly approached with neural networks using softmax and cross entropy. In this work, we are curious to see if introducing large-margins to neural language models would improve the perplexity and consequently word error rate in automatic speech recognition. Specifically, we first implement and test various types of conventional margins following the previous works in face recognition. To address the distribution of natural language data, we then compare different strategies for word vector norm-scaling. After that, we apply the best norm-scaling setup in combination with various margins and conduct neural language models rescoring experiments in automatic speech recognition. We find that although perplexity is slightly deteriorated, neural language models with large-margin softmax can yield word error rate similar to that of the standard softmax baseline. Finally, expected margins are analyzed through visualization of word vectors, showing that the syntactic and semantic relationships are also preserved. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech recognition

Two-way neural machine translation: A proof of concept for bidirectional translation modeling using a two-dimensional grid

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bahar, Parnia Brix, Christopher Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not easy to get the best effect for bidirectional translation, i.e., both source-to-target and target-to-source translation using a single model. If we exclude some pioneering attempts, such as multilingual systems, all other bidirectional translation approaches are required to train two individual models. This paper proposes to build a single end-to-end bidirectional translation model using a two-dimensional grid, where the left-to-right decoding generates source-to-target, and the bottom-to-up decoding creates target-to-source output. Instead of training two models independently, our approach encourages a single network to jointly learn to translate in both directions. Experiments on the WMT 2018 German↔English and Turkish↔English translation tasks show that the proposed model is capable of generating a good translation quality and has sufficient potential to direct the research. © 2020, CC-BY.

关键词： Decoding

Tight integrated end-to-end training for cascaded speech translation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bahar, Parnia Bieschke, Tobias Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers from error propagation between ASR and MT models. Direct speech translation is an alternative method to avoid error propagation;however, its performance is often behind the cascade system. To use an intermediate representation and preserve the end-to-end trainability, previous studies have proposed using two-stage models by passing the hidden vectors of the recognizer into the decoder of the MT model and ignoring the MT encoder. This work explores the feasibility of collapsing the entire cascade components into a single end-to-end trainable model by optimizing all parameters of ASR and MT models jointly without ignoring any learned parameters. It is a tightly integrated method that passes renormalized source word posterior distributions as a soft decision instead of one-hot vectors and enables backpropagation. Therefore, it provides both transcriptions and translations and achieves strong consistency between them. Our experiments on four tasks with different data scenarios show that the model outperforms cascade models up to 1.8% in BLEU and 2.0% in TER and is superior compared to direct models. © 2020, CC-BY.

关键词： Backpropagation

Neural data-To-Text generation via jointly learning the segmentation and correspondence

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shen, Xiaoyu Chang, Ernie Su, Hui Zhou, Jie Klakow, Dietrich Max Planck Institute for Informatics Department of Language Science and Technology Saarland Informatics Campus Pattern Recognition Center Wechat Ai Tencent Inc China

The neural attention model has achieved great success in data-To-Text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and "hallucination". Due to the black-box nature of the neural attention architecture, avoiding these problems in a systematic way is non-Trivial. To address this concern, we propose to explicitly segment target text into fragment units and align them with their data correspondences. The segmentation and correspondence are jointly learned as latent variables without any human annotations. We further impose a soft statistical constraint to regularize the segmental granularity. The resulting architecture maintains the same expressive power as neural attention models, while being able to generate fully interpretable outputs with several times less computational cost. On both E2E and WebNLG benchmarks, we show the proposed model consistently outperforms its neural attention counterparts. Copyright © 2020, The Authors. All rights reserved.

关键词：

When accurate prediction models yield harmful self-fulfilling prophecies

学校读者我要写书评

暂无评论

arXiv 2023年

作者： van Amsterdam, Wouter A.C. van Geloven, Nan Krijthe, Jesse H. Ranganath, Rajesh Cinà, Giovanni Department of Data Science and Biostatistics Julius Center of Health Sciences Primary Care University Medical Center Utrecht Heidelberglaan 100 Utrecht3584 CX Netherlands University of Utrecht Heidelberglaan 100 Utrecht3584 CX Netherlands Department of Biomedical Data Sciences Leiden University Medical Center Leiden Netherlands Pattern Recognition & Bioinformatics Delft University of Technology Delft Netherlands Courant Institute of Mathematical Science Department of Computer Science Center for Data Science New York University New York City United States Department of Medical Informatics Amsterdam University Medical Center Amsterdam Netherlands Institute for Logic Language and Computation University of Amsterdam Amsterdam Netherlands Pacmed Amsterdam Netherlands

Prediction models are popular in medical research and practice. By predicting an outcome of interest for specific patients, these models may help inform difficult treatment decisions, and are often hailed as the poster children for personalized, data-driven healthcare. We show however, that using prediction models for decision making can lead to harmful decisions, even when the predictions exhibit good discrimination after deployment. These models are harmful self-fulfilling prophecies: their deployment harms a group of patients but the worse outcome of these patients does not invalidate the predictive power of the model. Our main result is a formal characterization of a set of such prediction models. Next we show that models that are well calibrated before and after deployment are useless for decision making as they made no change in the data distribution. These results point to the need to revise standard practices for validation, deployment and evaluation of prediction models that are used in medical decisions. © 2023, CC BY.

关键词： Prediction models

Improved robustness to disfluencies in RNN-transducer based speech recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Mendelev, Valentin Raissi, Tina Camporese, Guglielmo Giollo, Manuel Amazon Alexa United States Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany Department of Mathematics "Tullio Levi-Civita" University of Padova Italy

Automatic Speech recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community. We investigate data selection and preparation choices aiming for improved robustness of RNN-T ASR to speech disfluencies with a focus on partial words. For evaluation we use clean data, data with disfluencies and a separate dataset with speech affected by stuttering. We show that after including a small amount of data with disfluencies in the training set the recognition accuracy on the tests with disfluencies and stuttering improves. Increasing the amount of training data with disfluencies gives additional gains without degradation on the clean data. We also show that replacing partial words with a dedicated token helps to get even better accuracy on utterances with disfluencies and stutter. The evaluation of our best model shows 22.5% and 16.4% relative WER reduction on those two evaluation sets. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech

Unsupervised training for large vocabulary translation using sparse lexicon and word classes

学校读者我要写书评

暂无评论

arXiv 2019年

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

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. Copyright © 2019, The Authors. All rights reserved.

关键词： Maximum principle

HTR-Flor: A Deep Learning System for Offline Handwritten Text recognition

学校读者我要写书评

暂无评论

HTR-Flor: A Deep Learning System for Offline Handwritten Tex...

Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI)

作者： Arthur Flor de Sousa Neto Byron Leite Dantas Bezerra Alejandro Héctor Toselli Estanislau Baptista Lima Escola Politécnica de Pernambuco Universidade de Pernambuco Recife Brazil Pattern Recognition and Human Language Technology Universitat Politècnica de València València Spain

ISBN: (数字)9781728192741

ISBN: (纸本)9781728192758

In recent years, Handwritten Text recognition (HTR) has captured a lot of attention among the researchers of the computer vision community. Current state-of-the-art approaches for offline HTR are based on Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, deep models such as CRNNs, Recur-rent Neural Networks (RNNs) are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. Besides, they usually have millions of parameters which require huge amount of data, and computational resource. Recently, a new class of neural net-work architecture, called Gated Convolutional Neural Networks (Gated-CNN), has demonstrated potentials to complement CRNN methods in modeling. Therefore, in this paper, we present a new architecture for HTR, based on Gated-CNN, with fewer parameters and fewer layers, which is able to outperform the current state-of-the-art architectures for HTR. The experiment validates that the proposed model has statistically significant recognition results, surpassing previous HTR systems by an average of 33% over five important handwritten benchmark datasets. Moreover, the proposed model is able to achieve satisfactory recognition rates even in case of few training data. Finally, its compact architecture requires less computational resources, which can be applied for real-world applications that have hardware limitations, such as robots and smartphones.

关键词： Logic gates Convolution Computer architecture Text recognition Hidden Markov models Optical imaging Computational modeling