发布求助
文献互助 智能选刊 最新文献

2013 IEEE Workshop on Automatic Speech Recognition and Understanding最新文献

筛选
英文 中文
Joint training of interpolated exponential n-gram models 插值指数n图模型的联合训练
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707700
A. Sethy, Stanley F. Chen, E. Arisoy, B. Ramabhadran, Kartik Audhkhasi, Shrikanth S. Narayanan, Paul Vozila
{"title":"Joint training of interpolated exponential n-gram models","authors":"A. Sethy, Stanley F. Chen, E. Arisoy, B. Ramabhadran, Kartik Audhkhasi, Shrikanth S. Narayanan, Paul Vozila","doi":"10.1109/ASRU.2013.6707700","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707700","url":null,"abstract":"For many speech recognition tasks, the best language model performance is achieved by collecting text from multiple sources or domains, and interpolating language models built separately on each individual corpus. When multiple corpora are available, it has also been shown that when using a domain adaptation technique such as feature augmentation [1], the performance on each individual domain can be improved by training a joint model across all of the corpora. In this paper, we explore whether improving each domain model via joint training also improves performance when interpolating the models together. We show that the diversity of the individual models is an important consideration, and propose a method for adjusting diversity to optimize overall performance. We present results using word n-gram models and Model M, a class-based n-gram model, and demonstrate improvements in both perplexity and word-error rate relative to state-of-the-art results on a Broadcast News transcription task.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126690312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
The TAO of ATWV: Probing the mysteries of keyword search performance ATWV的TAO:探索关键字搜索性能的奥秘
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707728
S. Wegmann, Arlo Faria, Adam L. Janin, K. Riedhammer, N. Morgan
{"title":"The TAO of ATWV: Probing the mysteries of keyword search performance","authors":"S. Wegmann, Arlo Faria, Adam L. Janin, K. Riedhammer, N. Morgan","doi":"10.1109/ASRU.2013.6707728","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707728","url":null,"abstract":"In this paper we apply diagnostic analysis to gain a deeper understanding of the performance of the the keyword search system that we have developed for conversational telephone speech in the IARPA Babel program. We summarize the Babel task, its primary performance metric, “actual term weighted value” (ATWV), and our recognition and keyword search systems. Our analysis uses two new oracle ATWV measures, a bootstrap-based ATWV confidence interval, and includes a study of the underpinnings of the large ATWV gains due to system combination. This analysis quantifies the potential ATWV gains from improving the number of true hits and the overall quality of the detection scores in our system's posting lists. It also shows that system combination improves our systems' ATWV via a small increase in the number of true hits in the posting lists.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"87 9 Suppl 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132658268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 47
Hierarchical neural networks and enhanced class posteriors for social signal classification 层次神经网络与增强类后验的社会信号分类
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707757
Raymond Brueckner, Björn Schuller
{"title":"Hierarchical neural networks and enhanced class posteriors for social signal classification","authors":"Raymond Brueckner, Björn Schuller","doi":"10.1109/ASRU.2013.6707757","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707757","url":null,"abstract":"With the impressive advances of deep learning in recent years the interest in neural networks has resurged in the fields of automatic speech recognition and emotion recognition. In this paper we apply neural networks to address speaker-independent detection and classification of laughter and filler vocalizations in speech. We first explore modeling class posteriors with standard neural networks and deep stacked autoencoders. Then, we adopt a hierarchical neural architecture to compute enhanced class posteriors and demonstrate that this approach introduces significant and consistent improvements on the Social Signals Sub-Challenge of the Interspeech 2013 Computational Paralinguistics Challenge (ComParE). On this task we achieve a value of 92.4% of the unweighted average area-under-the-curve, which is the official competition measure, on the test set. This constitutes an improvement of 9.1% over the baseline and is the best result obtained so far on this task.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130663355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 15
Deep maxout networks for low-resource speech recognition 低资源语音识别的深度最大输出网络
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707763
Yajie Miao, Florian Metze, Shourabh Rawat
{"title":"Deep maxout networks for low-resource speech recognition","authors":"Yajie Miao, Florian Metze, Shourabh Rawat","doi":"10.1109/ASRU.2013.6707763","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707763","url":null,"abstract":"As a feed-forward architecture, the recently proposed maxout networks integrate dropout naturally and show state-of-the-art results on various computer vision datasets. This paper investigates the application of deep maxout networks (DMNs) to large vocabulary continuous speech recognition (LVCSR) tasks. Our focus is on the particular advantage of DMNs under low-resource conditions with limited transcribed speech. We extend DMNs to hybrid and bottleneck feature systems, and explore optimal network structures (number of maxout layers, pooling strategy, etc) for both setups. On the newly released Babel corpus, behaviors of DMNs are extensively studied under different levels of data availability. Experiments show that DMNs improve low-resource speech recognition significantly. Moreover, DMNs introduce sparsity to their hidden activations and thus can act as sparse feature extractors.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133457477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 99
Semi-supervised bootstrapping approach for neural network feature extractor training 神经网络特征提取器训练的半监督自举方法
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707775
F. Grézl, M. Karafiát
{"title":"Semi-supervised bootstrapping approach for neural network feature extractor training","authors":"F. Grézl, M. Karafiát","doi":"10.1109/ASRU.2013.6707775","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707775","url":null,"abstract":"This paper presents bootstrapping approach for neural network training. The neural networks serve as bottle-neck feature extractor for subsequent GMM-HMM recognizer. The recognizer is also used for transcription and confidence assignment of untranscribed data. Based on the confidence, segments are selected and mixed with supervised data and new NNs are trained. With this approach, it is possible to recover 40-55% of the difference between partially and fully transcribed data (3 to 5% absolute improvement over NN trained on supervised data only). Using 70-85% of automatically transcribed segments with the highest confidence was found optimal to achieve this result.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133392264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 54
Probabilistic lexical modeling and unsupervised training for zero-resourced ASR 零资源ASR的概率词汇建模与无监督训练
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707771
Ramya Rasipuram, Marzieh Razavi, M. Magimai.-Doss
{"title":"Probabilistic lexical modeling and unsupervised training for zero-resourced ASR","authors":"Ramya Rasipuram, Marzieh Razavi, M. Magimai.-Doss","doi":"10.1109/ASRU.2013.6707771","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707771","url":null,"abstract":"Standard automatic speech recognition (ASR) systems rely on transcribed speech, language models, and pronunciation dictionaries to achieve state-of-the-art performance. The unavailability of these resources constrains the ASR technology to be available for many languages. In this paper, we propose a novel zero-resourced ASR approach to train acoustic models that only uses list of probable words from the language of interest. The proposed approach is based on Kullback-Leibler divergence based hidden Markov model (KL-HMM), grapheme subword units, knowledge of grapheme-to-phoneme mapping, and graphemic constraints derived from the word list. The approach also exploits existing acoustic and lexical resources available in other resource rich languages. Furthermore, we propose unsupervised adaptation of KL-HMM acoustic model parameters if untranscribed speech data in the target language is available. We demonstrate the potential of the proposed approach through a simulated study on Greek language.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133914607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition 基于深度学习的判别分段线性变换噪声鲁棒自动语音识别
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707755
Yosuke Kashiwagi, D. Saito, N. Minematsu, K. Hirose
{"title":"Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition","authors":"Yosuke Kashiwagi, D. Saito, N. Minematsu, K. Hirose","doi":"10.1109/ASRU.2013.6707755","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707755","url":null,"abstract":"In this paper, we propose the use of deep neural networks to expand conventional methods of statistical feature enhancement based on piecewise linear transformation. Stereo-based piecewise linear compensation for environments (SPLICE), which is a powerful statistical approach for feature enhancement, models the probabilistic distribution of input noisy features as a mixture of Gaussians. However, soft assignment of an input vector to divided regions is sometimes done inadequately and the vector comes to go through inadequate conversion. Especially when conversion has to be linear, the conversion performance will be easily degraded. Feature enhancement using neural networks is another powerful approach which can directly model a non-linear relationship between noisy and clean feature spaces. In this case, however, it tends to suffer from over-fitting problems. In this paper, we attempt to mitigate this problem by reducing the number of model parameters to estimate. Our neural network is trained whose output layer is associated with the states in the clean feature space, not in the noisy feature space. This strategy makes the size of the output layer independent of the kind of a given noisy environment. Firstly, we characterize the distribution of clean features as a Gaussian mixture model and then, by using deep neural networks, estimate discriminatively the state in the clean space that an input noisy feature corresponds to. Experimental evaluations using the Aurora 2 dataset demonstrate that our proposed method has the best performance compared to conventional methods.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"341 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115673587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
A hierarchical system for word discovery exploiting DTW-based initialization 利用基于dwt的初始化进行单词发现的分层系统
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707761
Oliver Walter, Timo Korthals, Reinhold Häb-Umbach, B. Raj
{"title":"A hierarchical system for word discovery exploiting DTW-based initialization","authors":"Oliver Walter, Timo Korthals, Reinhold Häb-Umbach, B. Raj","doi":"10.1109/ASRU.2013.6707761","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707761","url":null,"abstract":"Discovering the linguistic structure of a language solely from spoken input asks for two steps: phonetic and lexical discovery. The first is concerned with identifying the categorical subword unit inventory and relating it to the underlying acoustics, while the second aims at discovering words as repeated patterns of subword units. The hierarchical approach presented here accounts for classification errors in the first stage by modelling the pronunciation of a word in terms of subword units probabilistically: a hidden Markov model with discrete emission probabilities, emitting the observed subword unit sequences. We describe how the system can be learned in a completely unsupervised fashion from spoken input. To improve the initialization of the training of the word pronunciations, the output of a dynamic time warping based acoustic pattern discovery system is used, as it is able to discover similar temporal sequences in the input data. This improved initialization, using only weak supervision, has led to a 40% reduction in word error rate on a digit recognition task.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130532728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 38
Neighbour selection and adaptation for rapid speaker-dependent ASR 快速说话人依赖ASR的邻居选择与适应
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707706
Udhyakumar Nallasamy, Mark C. Fuhs, M. Woszczyna, Florian Metze, Tanja Schultz
{"title":"Neighbour selection and adaptation for rapid speaker-dependent ASR","authors":"Udhyakumar Nallasamy, Mark C. Fuhs, M. Woszczyna, Florian Metze, Tanja Schultz","doi":"10.1109/ASRU.2013.6707706","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707706","url":null,"abstract":"Speaker dependent (SD) ASR systems have significantly lower word error rates (WER) compared to speaker independent (SI) systems. However, SD systems require sufficient training data from the target speaker, which is impractical to collect in a short time. We present a technique for training SD models using just few minutes of speaker's data. We compensate for the lack of adequate speaker-specific data by selecting neighbours from a database of existing speakers who are acoustically close to the target speaker. These neighbours provide ample training data, which is used to adapt the SI model to obtain an initial SD model for the new speaker with significantly lower WER. We evaluate various neighbour selection algorithms on a large-scale medical transcription task and report significant reduction in WER using only 5 mins of speaker-specific data. We conduct a detailed analysis of various factors such as gender and accent in the neighbour selection. Finally, we study neighbour selection and adaptation in the context of discriminative objective functions.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129717422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Phonetic and anthropometric conditioning of MSA-KST cognitive impairment characterization system MSA-KST认知障碍表征系统的语音和人体测量调节
2013 IEEE Workshop on Automatic Speech Recognition and Understanding Pub Date : 2013-12-01 DOI: 10.1109/ASRU.2013.6707734
A. Ivanov, S. Jalalvand, R. Gretter, D. Falavigna
{"title":"Phonetic and anthropometric conditioning of MSA-KST cognitive impairment characterization system","authors":"A. Ivanov, S. Jalalvand, R. Gretter, D. Falavigna","doi":"10.1109/ASRU.2013.6707734","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707734","url":null,"abstract":"We explore the impact of speech- and speaker-specific modeling onto the Modulation Spectrum Analysis - Kolmogorov-Smirnov feature Testing (MSA-KST) characterization method in the task of automated prediction of the cognitive impairment diagnosis, namely dysphasia and pervasive development disorder. Phoneme-synchronous capturing of speech dynamics is a reasonable choice for a segmental speech characterization system as it allows comparing speech dynamics in the similar phonetic contexts. Speaker-specific modeling aims at reducing the “within-the-class” variability of the characterized speech or speaker population by removing the effect of speaker properties that should have no relation to the characterization. Specifically the vocal tract length of a speaker has nothing to do with the diagnosis attribution and, thus, the feature set shall be normalized accordingly. The resulting system compares favorably to the baseline system of the Interspeech'2013 Computational Paralinguistics Challenge.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125468980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信