Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430075
L. Deng
In this paper I argue that high-fidelity acoustic models have important roles to play in robust speech recognition in face of a multitude of variability ailing many current systems. The discussion of high-fidelity acoustic modeling is posited in the context of general statistical pattern recognition, in which the probabilistic-modeling component that embeds partial, imperfect knowledge is the fundamental building block enabling all other components including recognition error measure, decision rule, and training criterion. Within the session’s theme of acoustic modeling and robust speech recognition, I advance my argument using two concrete examples. First, an acoustic-modeling framework which embeds the knowledge of articulatory-like constraints is shown to be better able to account for the speech variability arising from varying speaking behavior (e.g., speaking rate and style) than without the use of the constraints. This higher-fidelity acoustic model is implemented in a multi-layer dynamic Bayesian network and computer simulation results are presented. Second, the variability in the acoustically distorted speech under adverse environments can be more precisely represented and more effectively handled using the information about phase asynchrony between the un-distorted speech and the mixing noise than without using such information. This high-fidelity, phase-sensitive acoustic distortion model is integrated into the same multi-layer Bayesian network but at separate, causally related layers from those representing the speaking-behavior variability. Related experimental results in the literature are reviewed, providing empirical support to the significant roles that the phase-sensitive model plays in environment-robust speech recognition.
{"title":"Roles of high-fidelity acoustic modeling in robust speech recognition","authors":"L. Deng","doi":"10.1109/ASRU.2007.4430075","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430075","url":null,"abstract":"In this paper I argue that high-fidelity acoustic models have important roles to play in robust speech recognition in face of a multitude of variability ailing many current systems. The discussion of high-fidelity acoustic modeling is posited in the context of general statistical pattern recognition, in which the probabilistic-modeling component that embeds partial, imperfect knowledge is the fundamental building block enabling all other components including recognition error measure, decision rule, and training criterion. Within the session’s theme of acoustic modeling and robust speech recognition, I advance my argument using two concrete examples. First, an acoustic-modeling framework which embeds the knowledge of articulatory-like constraints is shown to be better able to account for the speech variability arising from varying speaking behavior (e.g., speaking rate and style) than without the use of the constraints. This higher-fidelity acoustic model is implemented in a multi-layer dynamic Bayesian network and computer simulation results are presented. Second, the variability in the acoustically distorted speech under adverse environments can be more precisely represented and more effectively handled using the information about phase asynchrony between the un-distorted speech and the mixing noise than without using such information. This high-fidelity, phase-sensitive acoustic distortion model is integrated into the same multi-layer Bayesian network but at separate, causally related layers from those representing the speaking-behavior variability. Related experimental results in the literature are reviewed, providing empirical support to the significant roles that the phase-sensitive model plays in environment-robust speech recognition.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122927110","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430076
E. Zavarehei, S. Vaseghi
This paper presents a method for interpolation of lost speech segments. The short-time spectral amplitude (STSA) of speech is modeled using a linear prediction (LP) model of the spectral envelop and a harmonic plus noise model (HNM) of the excitation. The restoration algorithm is based on interpolation of the parameters of LP-HNM models of speech from both side of the gap. A codebook mapping (CBM) technique is used to fit the interpolated parameters to a pre-trained speech model. Experiments show that the CBM module mitigates the artifacts that may result from interpolation of relatively long speech gaps. Evaluations demonstrate that the proposed interpolation method results in a superior quality in comparison to alternative restoration methods.
{"title":"Interpolation of lost speech segments using LP-HNM model with codebook-mapping post-processing","authors":"E. Zavarehei, S. Vaseghi","doi":"10.1109/ASRU.2007.4430076","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430076","url":null,"abstract":"This paper presents a method for interpolation of lost speech segments. The short-time spectral amplitude (STSA) of speech is modeled using a linear prediction (LP) model of the spectral envelop and a harmonic plus noise model (HNM) of the excitation. The restoration algorithm is based on interpolation of the parameters of LP-HNM models of speech from both side of the gap. A codebook mapping (CBM) technique is used to fit the interpolated parameters to a pre-trained speech model. Experiments show that the CBM module mitigates the artifacts that may result from interpolation of relatively long speech gaps. Evaluations demonstrate that the proposed interpolation method results in a superior quality in comparison to alternative restoration methods.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128540146","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430105
A. Heidel, Lin-Shan Lee
We perform topic-based, unsupervised language model adaptation under an N-best rescoring framework by using previous-pass system hypotheses to infer a topic mixture which is used to select topic-dependent LMs for interpolation with a topic-independent LM. Our primary focus is on techniques for improving the robustness of topic inference for a given utterance with respect to recognition errors, including the use of ASR confidence and contextual information from surrounding utterances. We describe a novel application of metadata-based pseudo-story segmentation to language model adaptation, and present good improvements to character error rate on multi-genre GALE Project data in Mandarin Chinese.
{"title":"Robust topic inference for latent semantic language model adaptation","authors":"A. Heidel, Lin-Shan Lee","doi":"10.1109/ASRU.2007.4430105","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430105","url":null,"abstract":"We perform topic-based, unsupervised language model adaptation under an N-best rescoring framework by using previous-pass system hypotheses to infer a topic mixture which is used to select topic-dependent LMs for interpolation with a topic-independent LM. Our primary focus is on techniques for improving the robustness of topic inference for a given utterance with respect to recognition errors, including the use of ASR confidence and contextual information from surrounding utterances. We describe a novel application of metadata-based pseudo-story segmentation to language model adaptation, and present good improvements to character error rate on multi-genre GALE Project data in Mandarin Chinese.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128435068","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430148
M. Raab, R. Gruhn, E. Nöth
This paper presents a review of already collected non-native speech databases. Although the number of non-native speech databases is significantly less than the one of common speech databases, there were already a lot of data collection efforts taken at different institutes and companies. Because of the comparably small size of the databases, many of them are not available through the common distributors of speech corpora like ELDA or LDC. This leads to the fact that it is hard to keep an overview of what kind of databases have already been collected, and for what purposes there are still no collections. With this paper we hope to provide a useful resource regarding this issue.
{"title":"Non-native speech databases","authors":"M. Raab, R. Gruhn, E. Nöth","doi":"10.1109/ASRU.2007.4430148","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430148","url":null,"abstract":"This paper presents a review of already collected non-native speech databases. Although the number of non-native speech databases is significantly less than the one of common speech databases, there were already a lot of data collection efforts taken at different institutes and companies. Because of the comparably small size of the databases, many of them are not available through the common distributors of speech corpora like ELDA or LDC. This leads to the fact that it is hard to keep an overview of what kind of databases have already been collected, and for what purposes there are still no collections. With this paper we hope to provide a useful resource regarding this issue.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126908524","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430079
Chuan-Wei Ting, Jen-Tzung Chien
This paper presents a new streamed hidden Markov model (HMM) framework for speech recognition. The factor analysis (FA) is performed to discover the common factors of acoustic features. The streaming regularities are governed by the correlation between features, which is inherent in common factors. Those features corresponding to the same factor are generated by identical HMM state. Accordingly, we use multiple Markov chains to represent the variation trends in cepstral features. We develop a FA streamed HMM (FASHMM) and go beyond the conventional HMM assuming that all features at a speech frame conduct the same state emission. This streamed HMM is more delicate than the factorial HMM where the streaming was empirically determined. We also exploit a new decoding algorithm for FASHMM speech recognition. In this manner, we fulfill the flexible Markov chains for an input sequence of multivariate Gaussian mixture observations. In the experiments, the proposed method can reduce word error rate by 36% at most.
{"title":"Factor analysis of acoustic features for streamed hidden Markov modeling","authors":"Chuan-Wei Ting, Jen-Tzung Chien","doi":"10.1109/ASRU.2007.4430079","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430079","url":null,"abstract":"This paper presents a new streamed hidden Markov model (HMM) framework for speech recognition. The factor analysis (FA) is performed to discover the common factors of acoustic features. The streaming regularities are governed by the correlation between features, which is inherent in common factors. Those features corresponding to the same factor are generated by identical HMM state. Accordingly, we use multiple Markov chains to represent the variation trends in cepstral features. We develop a FA streamed HMM (FASHMM) and go beyond the conventional HMM assuming that all features at a speech frame conduct the same state emission. This streamed HMM is more delicate than the factorial HMM where the streaming was empirically determined. We also exploit a new decoding algorithm for FASHMM speech recognition. In this manner, we fulfill the flexible Markov chains for an input sequence of multivariate Gaussian mixture observations. In the experiments, the proposed method can reduce word error rate by 36% at most.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124701590","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430089
Shih-Hsiang Lin, Yao-ming Yeh, Berlin Chen
The performance of current automatic speech recognition (ASR) systems often deteriorates radically when the input speech is corrupted by various kinds of noise sources. Quite a few of techniques have been proposed to improve ASR robustness over the last few decades. Related work reported in the literature can be generally divided into two aspects according to whether the orientation of the methods is either from the feature domain or from the corresponding probability distributions. In this paper, we present a polynomial regression approach which has the merit of directly characterizing the relationship between the speech features and their corresponding probability distributions to compensate the noise effects. Two variants of the proposed approach are also extensively investigated as well. All experiments are conducted on the Aurora-2 database and task. Experimental results show that for clean-condition training, our approaches achieve considerable word error rate reductions over the baseline system, and also significantly outperform other conventional methods.
{"title":"Investigating the use of speech features and their corresponding distribution characteristics for robust speech recognition","authors":"Shih-Hsiang Lin, Yao-ming Yeh, Berlin Chen","doi":"10.1109/ASRU.2007.4430089","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430089","url":null,"abstract":"The performance of current automatic speech recognition (ASR) systems often deteriorates radically when the input speech is corrupted by various kinds of noise sources. Quite a few of techniques have been proposed to improve ASR robustness over the last few decades. Related work reported in the literature can be generally divided into two aspects according to whether the orientation of the methods is either from the feature domain or from the corresponding probability distributions. In this paper, we present a polynomial regression approach which has the merit of directly characterizing the relationship between the speech features and their corresponding probability distributions to compensate the noise effects. Two variants of the proposed approach are also extensively investigated as well. All experiments are conducted on the Aurora-2 database and task. Experimental results show that for clean-condition training, our approaches achieve considerable word error rate reductions over the baseline system, and also significantly outperform other conventional methods.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126790665","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430133
S. Tsakalidis, S. Matsoukas
Adaptive training under a Bayesian framework addresses some limitations of the standard maximum likelihood approaches. Also, the adaptively trained system can be directly used in unsupervised inference. The Bayesian framework uses a distribution of the transform rather than a point estimate. A continuous transform distribution makes the integral associated with the Bayesian framework intractable and therefore various approximations have been proposed. In this paper we model the transform distribution via a mixture of transforms. Under this model, the likelihood of an utterance is computed as a weighted sum of the likelihoods obtained by transforming its features based on each of the transforms in the mixture, with weights set to the transform priors. Experimental results on Arabic broadcast news exhibit increased likelihood on acoustic training data and improved speech recognition performance on unseen test data, compared to speaker independent and standard adaptive models.
{"title":"Bayesian adaptation in HMM training and decoding using a mixture of feature transforms","authors":"S. Tsakalidis, S. Matsoukas","doi":"10.1109/ASRU.2007.4430133","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430133","url":null,"abstract":"Adaptive training under a Bayesian framework addresses some limitations of the standard maximum likelihood approaches. Also, the adaptively trained system can be directly used in unsupervised inference. The Bayesian framework uses a distribution of the transform rather than a point estimate. A continuous transform distribution makes the integral associated with the Bayesian framework intractable and therefore various approximations have been proposed. In this paper we model the transform distribution via a mixture of transforms. Under this model, the likelihood of an utterance is computed as a weighted sum of the likelihoods obtained by transforming its features based on each of the transforms in the mixture, with weights set to the transform priors. Experimental results on Arabic broadcast news exhibit increased likelihood on acoustic training data and improved speech recognition performance on unseen test data, compared to speaker independent and standard adaptive models.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124350035","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430099
Jiazhong Nie, Runxin Li, D. Luo, Xihong Wu
As an important component in many speech and language processing applications, statistical language model has been widely investigated. The bigram topic model, which combines advantages of both the traditional n-gram model and the topic model, turns out to be a promising language modeling approach. However, the original bigram topic model assigns the same topic number for each context word but ignores the fact that there are different complexities to the latent semantics of context words, we present a new bigram topic model, the bigram PLSA model, and propose a modified training strategy that unevenly assigns latent topics to context words according to an estimation of their latent semantic complexities. As a consequence, a refined bigram PLSA model is reached. Experiments on HUB4 Mandarin test transcriptions reveal the superiority over existing models and further performance improvements on perplexity are achieved through the use of the refined bigram PLSA model.
{"title":"Refine bigram PLSA model by assigning latent topics unevenly","authors":"Jiazhong Nie, Runxin Li, D. Luo, Xihong Wu","doi":"10.1109/ASRU.2007.4430099","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430099","url":null,"abstract":"As an important component in many speech and language processing applications, statistical language model has been widely investigated. The bigram topic model, which combines advantages of both the traditional n-gram model and the topic model, turns out to be a promising language modeling approach. However, the original bigram topic model assigns the same topic number for each context word but ignores the fact that there are different complexities to the latent semantics of context words, we present a new bigram topic model, the bigram PLSA model, and propose a modified training strategy that unevenly assigns latent topics to context words according to an estimation of their latent semantic complexities. As a consequence, a refined bigram PLSA model is reached. Experiments on HUB4 Mandarin test transcriptions reveal the superiority over existing models and further performance improvements on perplexity are achieved through the use of the refined bigram PLSA model.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122745932","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430102
Wen Wang, A. Stolcke, Jing Zheng
In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from constraint dependency grammar parses, tightly integrate knowledge of words, morphological and lexical features, and syntactic dependency constraints. Two structured language models are applied for N-best rescoring, one is an almost-parsing language model, and the other utilizes more syntactic features by explicitly modeling syntactic dependencies between words. We also investigate effective and efficient language modeling methods to use N-grams extracted from up to 1 teraword of web documents. We apply all these language models for N-best re-ranking on the NIST and DARPA GALE program1 2006 and 2007 machine translation evaluation tasks and find that the combination of these language models increases the BLEU score up to 1.6% absolutely on blind test sets.
{"title":"Reranking machine translation hypotheses with structured and web-based language models","authors":"Wen Wang, A. Stolcke, Jing Zheng","doi":"10.1109/ASRU.2007.4430102","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430102","url":null,"abstract":"In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from constraint dependency grammar parses, tightly integrate knowledge of words, morphological and lexical features, and syntactic dependency constraints. Two structured language models are applied for N-best rescoring, one is an almost-parsing language model, and the other utilizes more syntactic features by explicitly modeling syntactic dependencies between words. We also investigate effective and efficient language modeling methods to use N-grams extracted from up to 1 teraword of web documents. We apply all these language models for N-best re-ranking on the NIST and DARPA GALE program1 2006 and 2007 machine translation evaluation tasks and find that the combination of these language models increases the BLEU score up to 1.6% absolutely on blind test sets.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129515996","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}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430182
N. Kitaoka, Kazumasa Yamamoto, Tomohiro Kusamizu, S. Nakagawa, Takeshi Yamada, S. Tsuge, C. Miyajima, T. Nishiura, M. Nakayama, Y. Denda, M. Fujimoto, T. Takiguchi, S. Tamura, S. Kuroiwa, K. Takeda, Satoshi Nakamura
Voice activity detection (VAD) plays an important role in speech processing including speech recognition, speech enhancement, and speech coding in noisy environments. We developed an evaluation framework for VAD in such environments, called corpus and environment for noisy speech recognition 1 concatenated (CENSREC-1-C). This framework consists of noisy continuous digit utterances and evaluation tools for VAD results. By adoptiong two evaluation measures, one for frame-level detection performance and the other for utterance-level detection performance, we provide the evaluation results of a power-based VAD method as a baseline. When using VAD in speech recognizer, the detected speech segments are extended to avoid the loss of speech frames and the pause segments are then absorbed by a pause model. We investigate the balance of an explicit segmentation by VAD and an implicit segmentation by a pause model using an experimental simulation of segment extension and show that a small extension improves speech recognition.
{"title":"Development of VAD evaluation framework CENSREC-1-C and investigation of relationship between VAD and speech recognition performance","authors":"N. Kitaoka, Kazumasa Yamamoto, Tomohiro Kusamizu, S. Nakagawa, Takeshi Yamada, S. Tsuge, C. Miyajima, T. Nishiura, M. Nakayama, Y. Denda, M. Fujimoto, T. Takiguchi, S. Tamura, S. Kuroiwa, K. Takeda, Satoshi Nakamura","doi":"10.1109/ASRU.2007.4430182","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430182","url":null,"abstract":"Voice activity detection (VAD) plays an important role in speech processing including speech recognition, speech enhancement, and speech coding in noisy environments. We developed an evaluation framework for VAD in such environments, called corpus and environment for noisy speech recognition 1 concatenated (CENSREC-1-C). This framework consists of noisy continuous digit utterances and evaluation tools for VAD results. By adoptiong two evaluation measures, one for frame-level detection performance and the other for utterance-level detection performance, we provide the evaluation results of a power-based VAD method as a baseline. When using VAD in speech recognizer, the detected speech segments are extended to avoid the loss of speech frames and the pause segments are then absorbed by a pause model. We investigate the balance of an explicit segmentation by VAD and an implicit segmentation by a pause model using an experimental simulation of segment extension and show that a small extension improves speech recognition.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134097038","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：