检索结果-内蒙古大学图书馆

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

学校读者我要写书评

暂无评论

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

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

Probing the information encoded in x-vectors

学校读者我要写书评

暂无评论

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

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

关键词： Embeddings

Spoken language Recognition using X-vectors

学校读者我要写书评

暂无评论

Spoken Language Recognition using X-vectors

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

Zero Resource Speaking Rate Estimation from Change Point Detection of Syllable-like Units 44

学校读者我要写书评

暂无评论

Zero Resource Speaking Rate Estimation from Change Point Det...

44th IEEE International Conference on Acoustics, speech, and Signal processing, ICASSP 2019

作者： Nayak, Shekhar Bhati, Saurabhchand Rama Murty, K. Sri Department of Electrical Engineering Indian Institute of Technology Hyderabad India Center for Language and Speech Processing Johns Hopkins University United States

ISBN: (纸本)9781479981311

Speaking rate is an important attribute of the speech signal which plays a crucial role in the performance of automatic speech processing systems. In this paper, we propose to estimate the speaking rate by segmenting the speech into syllable-like units using end point detection algorithms which do not require any training and fine-tuning. Also, there are no predefined constraints on the expected number of syllabic segments. The acoustic subword units are obtained only from speech signal to estimate the speaking rate without any requirement of transcriptions or phonetic knowledge of the speech data. A recent theta-rate oscillator based syllabification algorithm is also employed for speaking rate estimation. The performance is evaluated on TIMIT corpus and spontaneous speech from Switchboard corpus. The correlation results are comparable to recent algorithms which are trained with specific training set and/or make use of the available transcriptions. © 2019 IEEE.

关键词： Point contacts

Performance monitoring for end-to-end speech recognition

学校读者我要写书评

暂无评论

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

Exploring methods for the automatic detection of errors in manual transcription

学校读者我要写书评

暂无评论

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

A practical two-stage training strategy for multi-stream end-to-end speech recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Ruizhi Sell, Gregory Wang, Xiaofei Watanabe, Shinji Hermansky, Hynek Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States Speech and Dialog Research Group Microsoft United States

The multi-stream paradigm of audio processing, in which several sources are simultaneously considered, has been an active research area for information fusion. Our previous study offered a promising direction within end-to-end automatic speech recognition, where parallel encoders aim to capture diverse information followed by a stream-level fusion based on attention mechanisms to combine the different views. However, with an increasing number of streams resulting in an increasing number of encoders, the previous approach could require substantial memory and massive amounts of parallel data for joint training. In this work, we propose a practical two-stage training scheme. Stage-1 is to train a Universal Feature Extractor (UFE), where encoder outputs are produced from a single-stream model trained with all data. Stage-2 formulates a multi-stream scheme intending to solely train the attention fusion module using the UFE features and pretrained components from Stage-1. Experiments have been conducted on two datasets, DIRHA and AMI, as a multi-stream scenario. Compared with our previous method, this strategy achieves relative word error rate reductions of 8.2-32.4%, while consistently outperforming several conventional combination methods. Copyright © 2019, The Authors. All rights reserved.

关键词： speech recognition

A synthetic recipe for OCR 15

学校读者我要写书评

暂无评论

A synthetic recipe for OCR

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

作者： Etter, David Rawls, Stephen Carpenter, Cameron Sell, Gregory Human Language Technology Center of Excellence Johns Hopkins University Baltimore United States Information Science Institute University of Southern California United States

ISBN: (纸本)9781728128610

Synthetic data generation for optical character recognition (OCR) promises unlimited training data at zero annotation cost. With enough fonts and seed text, we should be able to generate data to train a model that approaches or exceeds the performance with real annotated data. Unfortunately, this is not always the reality. Unconstrained image settings, such as internet memes, scanned web pages, or newspapers, present diverse scripts, fonts, layouts, and complex backgrounds, which cause models trained with synthetic data to break down. In this work, we investigate the synthetic image generation problem on a large multilingual set of unconstrained document images. Our work presents a comprehensive evaluation of the impact of synthetic data attributes on model performance. The results provide a recipe for synthetic data generation that will help guide future research. © 2019 IEEE.

关键词： Optical character recognition

Optical Character Recognition with Chinese and Korean Character Decomposition

学校读者我要写书评

暂无评论

Optical Character Recognition with Chinese and Korean Charac...

International Conference on Document Analysis and Recognition Workshops (ICDARW)

作者： Chun-Chieh Chang Ashish Arora Leibny Paola Garcia Perera David Etter Daniel Povey Sanjeev Khudanpur Johns Hopkins University Baltimore MD USA Center for Language and Speech Processing Johns Hopkins University Baltimore USA Human Language Technology Center of Excellence Johns Hopkins University Baltimore USA

ISBN: (纸本)9781728150550

We present our work on Optical Character Recognition on Chinese and Korean Characters for line level transcriptions. One challenge for recognizing Chinese and Korean is that there are thousands of characters for a system to recognize. In addition, many uncommon characters only appear a couple of times in training. We use character decomposition methods to break characters into smaller constituent graphemes. CangJie is used for Chinese character decomposition and Korean Jamo is used for Korean character decomposition. Character decomposition reduces the size of the Neural Network models and allows training examples to be shared across uncommon characters with the same graphemes. We report that a CNN-TDNN neural network model using character decomposition has significantly fewer parameters than the baseline while also improving character error rate.

关键词： Optical character recognition software Hidden Markov models Training Adaptive optics Character recognition Simultaneous localization and mapping speech recognition