检索结果-内蒙古大学图书馆

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Desh Raj David Snyder Daniel Povey Sanjeev Khudanpur Center for Language and Speech Processing & Human Language Technology Center of Excellence The Johns Hopkins University Baltimore MD USA

ISBN: (数字)9781728103068

ISBN: (纸本)9781728103075

Deep neural network based speaker embeddings, such as x-vectors, have been shown to perform well in text-independent speaker recognition/verification tasks. In this paper, we use simple classifiers to investigate the contents encoded by x-vector embeddings. We probe these embeddings for information related to the speaker, channel, transcription (sentence, words, phones), and meta information about the utterance (duration and augmentation type), and compare these with the information encoded by i-vectors across a varying number of dimensions. We also study the effect of data augmentation during extractor training on the information captured by x-vectors. Experiments on the RedDots data set show that x-vectors capture spoken content and channel-related information, while performing well on speaker verification tasks.

关键词： Task analysis Probes Data mining Speaker recognition Feature extraction Neural networks speech recognition

来源：评论

学校读者我要写书评

暂无评论

Using ASR methods for OCR 15

Using ASR methods for OCR

引用

15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

作者： Arora, Ashish Garcia, Paola Watanabe, Shinji Manohar, Vimal Shao, Yiwen Khudanpur, Sanjeev Chang, Chun Chieh Rekabdar, Babak Babaali, Bagher Povey, Daniel Etter, David Raj, Desh Hadian, Hossein Trmal, Jan Center for Language and Speech Processing Johns Hopkins University Baltimore United States Human Language Technology Center of Excellence Johns Hopkins University Baltimore United States Department of Computer Engineering Sharif University of Technology Iran School of Mathematics Statistics and Computer Sciences College of Science University of Tehran Iran

ISBN: (纸本)9781728128610

Hybrid deep neural network hidden Markov models (DNN-HMM) have achieved impressive results on large vocabulary continuous speech recognition (LVCSR) tasks. However, the recent approaches using DNN-HMM models are not explored much for text recognition. Inspired by the current work in automatic speech recognition (ASR) and machine translation, we present an open vocabulary sub-word text recognition system. The sub-word lexicon and sub-word language model (LM) helps in overcoming the challenge of recognizing out of vocabulary (OOV) words, and a time delay neural network (TDNN) and convolution neural network (CNN) based DNN-HMM optical model (OM) efficiently models the sequence dependency in the line image. We present results on 12 datasets with training data varying from 6k lines to 600k lines. The system is built for 8 languages, i.e., English, French, Arabic, Chinese, Farsi, Tamil, Russian, and Korean. We report competitive results on several commonly used handwritten and printed text datasets. © 2019 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Approaches to Evaluate Parkinsonian speech Using Artificial Models 1st

Approaches to Evaluate Parkinsonian Speech Using Artificial ...

引用

1st Automatic Assessment of Parkinsonian speech Workshop, AAPS 2019

作者： Godino-Llorente, J.I. Moro-Velázquez, L. Gómez-García, J.A. Choi, Jeung-Yoon Dehak, N. Shattuck-Hufnagel, S. Theory and Communications Department Universidad Politécnica de Madrid C/ Nikola Tesla s/n Madrid28031 Spain Center for Language and Speech Processing Johns Hopkins University 3400 North Charles Street BaltimoreMD21218-2680 United States Speech Communication Group Massachusetts Institute of Technology 50 Vassar St. CambridgeMA02139-4307 United States

ISBN: (纸本)9783030656539

Our preliminary data and experiments show the potentiality of the artificial intelligence techniques to identify Parkinson’s disease and to assess its extent using the information extracted from the speech. Our conclusions are based on several prospective studies with different corpora of parkinsonian and control subjects modelled following different approaches, mainly grounded on articulatory aspects of the speech and on the use of probabilistic generative models inspired in those used in the field of speaker recognition. Results obtained are consistent among the different approaches and corpora, providing detection accuracies over 85%. This chapter compiles and compares the approaches we followed and the results we obtained in the last few years, and discusses some key aspects for future research in the field. The goal is not only to demonstrate the potentiality of the artificial intelligence techniques used, but also to extract from them significant knowledge that might be of interest for our understanding of the effects of the disease on the speech. To this respect a phonemic analysis based on the automatic techniques developed is carried out, suggesting important cues about the acoustic units that are more affected by the disease. © 2020, Springer Nature Switzerland AG.

关键词： speech recognition

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Pronunciation Lexicons for Cross-language Acoustic Model Transfer

Zero-Shot Pronunciation Lexicons for Cross-Language Acoustic...

引用

IEEE Workshop on Automatic speech Recognition and Understanding

作者： Matthew Wiesner Oliver Adams David Yarowsky Jan Trmal Sanjeev Khudanpur Center for Language and Speech Processing The Johns Hopkins University USA Human Language Technology Center of Excellence The Johns Hopkins University USA

ISBN: (数字)9781728103068

ISBN: (纸本)9781728103075

Existing acoustic models can be transferred to any language with a pronunciation lexicon (lexicon) that uses the same set of sub-word units as in training. Unfortunately such lexicons are not readily available in many low-resource languages. We bypass this requirement and create lexicons by training a grapheme-to-phoneme (G2P) transducer on a subset of words from other languages for which pronunciations are available. The subset of words is selected based on how representative it is of target language text. We find that cross-language acoustic model transfer using our selection strategy outperforms selection based on language similarity, and results in ASR performance approaching that of hand-crafted rule based lexicons in the majority of cases.

关键词： Training Silicon Acoustics Measurement Error analysis Optimization Greedy algorithms

来源：评论

学校读者我要写书评

暂无评论

Analysis of Robustness of Deep Single-Channel speech Separation Using Corpora Constructed From Multiple Domains

Analysis of Robustness of Deep Single-Channel Speech Separat...

引用

IEEE Workshop on Applications of Signal processing to Audio and Acoustics

作者： Matthew Maciejewski Gregory Sell Yusuke Fujita Leibny Paola Garcia-Perera Shinji Watanabe Sanjeev Khudanpur Center for Language and Speech Processing The Johns Hopkins University USA Human Language Technology Center of Excellence The Johns Hopkins University USA

Deep-learning based single-channel speech separation has been studied with great success, though evaluations have typically been limited to relatively controlled environments based on clean, near-field, and read speech. This work investigates the robustness of such representative techniques in more realistic environments with multiple and diverse conditions. To this end, we first construct datasets from the Mixer 6 and CHiME-5 corpora, featuring studio interviews and dinner parties respectively, using a procedure carefully designed to generate desirable synthetic overlap data sufficient for evaluation as well as for training deep learning models. Using these new datasets, we demonstrate the substantial shortcomings in mismatched conditions of these separation techniques. Though multi-condition training greatly mitigated the performance degradation in near-field conditions, one of the important findings is that both matched and multi-condition training have significant gaps from the oracle performance in far-field conditions, which advocates a need for extending existing separation techniques to deal with far-field/highly-reverberant speech mixtures.

关键词： Mixers Training Microphones Robustness speech recognition Conferences Signal processing

来源：评论

学校读者我要写书评

暂无评论

Probing the information encoded in x-vectors

arXiv

引用

arXiv 2019年

作者： Raj, Desh Snyder, David Povey, Daniel Khudanpur, Sanjeev Center for Language and Speech Processing & Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD21218 United States

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Spoken language Recognition using X-vectors

Spoken Language Recognition using X-vectors

引用

2018 Speaker and language Recognition Workshop, ODYSSEY 2018

作者： Snyder, David Garcia-Romero, Daniel McCree, Alan Sell, Gregory Povey, Daniel Khudanpur, Sanjeev Center for Language and Speech Processing Human Language Technology Center of Excellence The Johns Hopkins University United States

In this paper, we apply x-vectors to the task of spoken language recognition. This framework consists of a deep neural network that maps sequences of speech features to fixed-dimensional embeddings, called x-vectors. Long-term language characteristics are captured in the network by a temporal pooling layer that aggregates information across time. Once extracted, x-vectors utilize the same classification technology developed for i-vectors. In the 2017 NIST language recognition evaluation, x-vectors achieved excellent results and outperformed our state-of-the-art i-vector systems. In the post-evaluation analysis presented here, we experiment with several variations of the x-vector framework, and find that the best performing system uses multilingual bottleneck features, data augmentation, and a discriminative Gaussian classifier. © ODYSSEY 2018. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Transformer-Based Neural language Model Adaptation

An Empirical Study of Transformer-Based Neural Language Mode...

引用

IEEE International Conference on Acoustics, speech and Signal processing

作者： Ke Li Zhe Liu Tianxing He Hongzhao Huang Fuchun Peng Daniel Povey Sanjeev Khudanpur Facebook AI Menlo Park CA USA Massachusetts Institute of Technology Cambridge MA USA Center for Language and Speech Processing Johns Hopkins University Baltimore MD USA

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

We explore two adaptation approaches of deep Transformer based neural language models (LMs) for automatic speech recognition. The first approach is a pretrain-finetune framework, where we first pretrain a Transformer LM on a large-scale text corpus from scratch and then adapt it to relatively small target domains via finetuning. The second approach is a mixer of dynamically weighted models that are separately trained on source and target domains, aiming to improve simple linear interpolation with dynamic weighting. We compare the two approaches with three baselines - without adaptation, merging data, and simple interpolation - on Switchboard (SWBD) and Wall Street Journal (WSJ). Experiments show that the mixer model generally performs better than baselines and finetuning. Compared with no adaptation, finetuning and the mixer approach obtain up to relative 11.5% and 14.1% WER reductions on SWBD, respectively. The mixer model also outperforms linear interpolation and merging data. On WSJ, the mixer approach achieves a new state-of-the-art WER result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring methods for the automatic detection of errors in manual transcription

arXiv

引用

arXiv 2019年

作者： Wang, Xiaofei Yang, Jinyi Li, Ruizhi Sadhu, Samik Hermansky, Hynek Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States

Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in manual transcriptions not only saves time and labors but benefits the performance of tasks that need the training process. Inspired by the success of hybrid automatic speech recognition using both language model and acoustic model, two approaches of automatic error detection in the transcriptions have been explored in this work. Previous study using a biased language model approach, relying on a strong transcription-dependent language model, has been reviewed. In this work, we propose a novel acoustic model based approach, focusing on the phonetic sequence of speech. Both methods have been evaluated on a completely real dataset, which was originally transcribed with errors and strictly corrected manually afterwards. Copyright © 2019, The Authors. All rights reserved.

关键词： Error detection

来源：评论

学校读者我要写书评

暂无评论

Performance monitoring for end-to-end speech recognition

arXiv

引用

arXiv 2019年

作者： Li, Ruizhi Sell, Gregory Hermansky, Hynek Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States

Measuring performance of an automatic speech recognition (ASR) system without ground-truth could be beneficial in many scenarios, especially with data from unseen domains, where performance can be highly inconsistent. In conventional ASR systems, several performance monitoring (PM) techniques have been well-developed to monitor performance by looking at triphone posteriors or pre-softmax activations from neural network acoustic modeling. However, strategies for monitoring more recently developed end-to-end ASR systems have not yet been explored, and so that is the focus of this paper. We adapt previous PM measures (Entropy, M-measure and Autoencoder) and apply our proposed RNN predictor in the end-to-end setting. These measures utilize the decoder output layer and attention probability vectors, and their predictive power is measured with simple linear models. Our findings suggest that decoder-level features are more feasible and informative than attention-level probabilities for PM measures, and that M-measure on the decoder posteriors achieves the best overall predictive performance with an average prediction error 8.8%. Entropy measures and RNN-based prediction also show competitive predictability, especially for unseen conditions. Copyright © 2019, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：