Pub Date : 2012-12-01DOI: 10.1109/SLT.2012.6424248
João Miranda, J. Neto, A. Black
In this work we present a set of techniques which explore information from multiple, different language versions of the same speech, to improve Automatic Speech Recognition (ASR) performance. Using this redundant information we are able to recover acronyms, words that cannot be found in the multiple hypotheses produced by the ASR systems, and pronunciations absent from their pronunciation dictionaries. When used together, the three techniques yield a relative improvement of 5.0% over the WER of our baseline system, and 24.8% relative when compared with standard speech recognition, in an Europarl Committee dataset with three different languages (Portuguese, Spanish and English). One full iteration of the system has a parallel Real Time Factor (RTF) of 3.08 and a sequential RTF of 6.44.
{"title":"Recovery of acronyms, out-of-lattice words and pronunciations from parallel multilingual speech","authors":"João Miranda, J. Neto, A. Black","doi":"10.1109/SLT.2012.6424248","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424248","url":null,"abstract":"In this work we present a set of techniques which explore information from multiple, different language versions of the same speech, to improve Automatic Speech Recognition (ASR) performance. Using this redundant information we are able to recover acronyms, words that cannot be found in the multiple hypotheses produced by the ASR systems, and pronunciations absent from their pronunciation dictionaries. When used together, the three techniques yield a relative improvement of 5.0% over the WER of our baseline system, and 24.8% relative when compared with standard speech recognition, in an Europarl Committee dataset with three different languages (Portuguese, Spanish and English). One full iteration of the system has a parallel Real Time Factor (RTF) of 3.08 and a sequential RTF of 6.44.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129270522","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424197
J. Williams
This paper examines two statistical spoken dialog systems deployed to the public, extending an earlier study on one system [1]. Results across the two systems show that statistical techniques improved performance in some cases, but degraded performance in others. Investigating degradations, we find the three main causes are (non-obviously) inaccurate parameter estimates, poor confidence scores, and correlations in speech recognition errors. We also find evidence for fundamental weaknesses in the formulation of the model as a generative process, and briefly show the potential of a discriminatively-trained alternative.
{"title":"A critical analysis of two statistical spoken dialog systems in public use","authors":"J. Williams","doi":"10.1109/SLT.2012.6424197","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424197","url":null,"abstract":"This paper examines two statistical spoken dialog systems deployed to the public, extending an earlier study on one system [1]. Results across the two systems show that statistical techniques improved performance in some cases, but degraded performance in others. Investigating degradations, we find the three main causes are (non-obviously) inaccurate parameter estimates, poor confidence scores, and correlations in speech recognition errors. We also find evidence for fundamental weaknesses in the formulation of the model as a generative process, and briefly show the potential of a discriminatively-trained alternative.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132480743","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424208
Taehwan Kim, Karen Livescu, Gregory Shakhnarovich
We study the recognition of fingerspelling sequences in American Sign Language from video using tandem-style models, in which the outputs of multilayer perceptron (MLP) classifiers are used as observations in a hidden Markov model (HMM)-based recognizer. We compare a baseline HMM-based recognizer, a tandem recognizer using MLP letter classifiers, and a tandem recognizer using MLP classifiers of phonological features. We present experiments on a database of fingerspelling videos. We find that the tandem approaches outperform an HMM-based baseline, and that phonological feature-based tandem models outperform letter-based tandem models.
{"title":"American sign language fingerspelling recognition with phonological feature-based tandem models","authors":"Taehwan Kim, Karen Livescu, Gregory Shakhnarovich","doi":"10.1109/SLT.2012.6424208","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424208","url":null,"abstract":"We study the recognition of fingerspelling sequences in American Sign Language from video using tandem-style models, in which the outputs of multilayer perceptron (MLP) classifiers are used as observations in a hidden Markov model (HMM)-based recognizer. We compare a baseline HMM-based recognizer, a tandem recognizer using MLP letter classifiers, and a tandem recognizer using MLP classifiers of phonological features. We present experiments on a database of fingerspelling videos. We find that the tandem approaches outperform an HMM-based baseline, and that phonological feature-based tandem models outperform letter-based tandem models.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131385037","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424215
Alex Marin, T. Kwiatkowski, Mari Ostendorf, Luke Zettlemoyer
This paper addresses the problem of detecting words that are out-of-vocabulary (OOV) for a speech recognition system to improve automatic speech translation. The detection system leverages confidence prediction techniques given a confusion network representation and parsing with OOV word tokens to identify spans associated with true OOV words. Working in a resource-constrained domain, we achieve OOV detection F-scores of 60-66 and reduce word error rate by 12% relative to the case where OOV words are not detected.
{"title":"Using syntactic and confusion network structure for out-of-vocabulary word detection","authors":"Alex Marin, T. Kwiatkowski, Mari Ostendorf, Luke Zettlemoyer","doi":"10.1109/SLT.2012.6424215","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424215","url":null,"abstract":"This paper addresses the problem of detecting words that are out-of-vocabulary (OOV) for a speech recognition system to improve automatic speech translation. The detection system leverages confidence prediction techniques given a confusion network representation and parsing with OOV word tokens to identify spans associated with true OOV words. Working in a resource-constrained domain, we achieve OOV detection F-scores of 60-66 and reduce word error rate by 12% relative to the case where OOV words are not detected.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123322676","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424210
Jinyu Li, Dong Yu, J. Huang, Y. Gong
Context-dependent deep neural network hidden Markov model (CD-DNN-HMM) is a recently proposed acoustic model that significantly outperformed Gaussian mixture model (GMM)-HMM systems in many large vocabulary speech recognition (LVSR) tasks. In this paper we present our strategy of using mixed-bandwidth training data to improve wideband speech recognition accuracy in the CD-DNN-HMM framework. We show that DNNs provide the flexibility of using arbitrary features. By using the Mel-scale log-filter bank features we not only achieve higher recognition accuracy than using MFCCs, but also can formulate the mixed-bandwidth training problem as a missing feature problem, in which several feature dimensions have no value when narrowband speech is presented. This treatment makes training CD-DNN-HMMs with mixed-bandwidth data an easy task since no bandwidth extension is needed. Our experiments on voice search data indicate that the proposed solution not only provides higher recognition accuracy for the wideband speech but also allows the same CD-DNN-HMM to recognize mixed-bandwidth speech. By exploiting mixed-bandwidth training data CD-DNN-HMM outperforms fMPE+BMMI trained GMM-HMM, which cannot benefit from using narrowband data, by 18.4%.
{"title":"Improving wideband speech recognition using mixed-bandwidth training data in CD-DNN-HMM","authors":"Jinyu Li, Dong Yu, J. Huang, Y. Gong","doi":"10.1109/SLT.2012.6424210","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424210","url":null,"abstract":"Context-dependent deep neural network hidden Markov model (CD-DNN-HMM) is a recently proposed acoustic model that significantly outperformed Gaussian mixture model (GMM)-HMM systems in many large vocabulary speech recognition (LVSR) tasks. In this paper we present our strategy of using mixed-bandwidth training data to improve wideband speech recognition accuracy in the CD-DNN-HMM framework. We show that DNNs provide the flexibility of using arbitrary features. By using the Mel-scale log-filter bank features we not only achieve higher recognition accuracy than using MFCCs, but also can formulate the mixed-bandwidth training problem as a missing feature problem, in which several feature dimensions have no value when narrowband speech is presented. This treatment makes training CD-DNN-HMMs with mixed-bandwidth data an easy task since no bandwidth extension is needed. Our experiments on voice search data indicate that the proposed solution not only provides higher recognition accuracy for the wideband speech but also allows the same CD-DNN-HMM to recognize mixed-bandwidth speech. By exploiting mixed-bandwidth training data CD-DNN-HMM outperforms fMPE+BMMI trained GMM-HMM, which cannot benefit from using narrowband data, by 18.4%.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127735459","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424241
Sriram Ganapathy, M. Omar, Jason W. Pelecanos
Language identification (LID) of speech data recorded over noisy communication channels is a challenging problem especially when the LID system is tested on speech data from an unseen communication channel (not seen in training). In this paper, we consider the scenario in which a small amount of adaptation data is available from a new communication channel. Various approaches are investigated for efficient utilization of the adaptation data in a supervised as well as unsupervised setting. In a supervised adaptation framework, we show that support vector machines (SVMs) with higher order polynomial kernels (HO-SVM) trained using lower dimensional representations of the the Gaussian mixture model supervectors (GSVs) provide significant performance improvements over the baseline SVM-GSV system. In these LID experiments, we obtain 30% reduction in error-rate with 6 hours of adaptation data for a new channel. For unsupervised adaptation, we develop an iterative procedure for re-labeling the development data using a co-training framework. In these experiments, we obtain considerable improvements(relative improvements of 13 %) over a self-training framework with the HO-SVM models.
{"title":"Noisy channel adaptation in language identification","authors":"Sriram Ganapathy, M. Omar, Jason W. Pelecanos","doi":"10.1109/SLT.2012.6424241","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424241","url":null,"abstract":"Language identification (LID) of speech data recorded over noisy communication channels is a challenging problem especially when the LID system is tested on speech data from an unseen communication channel (not seen in training). In this paper, we consider the scenario in which a small amount of adaptation data is available from a new communication channel. Various approaches are investigated for efficient utilization of the adaptation data in a supervised as well as unsupervised setting. In a supervised adaptation framework, we show that support vector machines (SVMs) with higher order polynomial kernels (HO-SVM) trained using lower dimensional representations of the the Gaussian mixture model supervectors (GSVs) provide significant performance improvements over the baseline SVM-GSV system. In these LID experiments, we obtain 30% reduction in error-rate with 6 hours of adaptation data for a new channel. For unsupervised adaptation, we develop an iterative procedure for re-labeling the development data using a co-training framework. In these experiments, we obtain considerable improvements(relative improvements of 13 %) over a self-training framework with the HO-SVM models.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127871347","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424242
R. Takashima, T. Takiguchi, Y. Ariki
This paper presents a voice conversion (VC) technique for noisy environments, where parallel exemplars are introduced to encode the source speech signal and synthesize the target speech signal. The parallel exemplars (dictionary) consist of the source exemplars and target exemplars, having the same texts uttered by the source and target speakers. The input source signal is decomposed into the source exemplars, noise exemplars obtained from the input signal, and their weights (activities). Then, by using the weights of the source exemplars, the converted signal is constructed from the target exemplars. We carried out speaker conversion tasks using clean speech data and noise-added speech data. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based method.
{"title":"Exemplar-based voice conversion in noisy environment","authors":"R. Takashima, T. Takiguchi, Y. Ariki","doi":"10.1109/SLT.2012.6424242","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424242","url":null,"abstract":"This paper presents a voice conversion (VC) technique for noisy environments, where parallel exemplars are introduced to encode the source speech signal and synthesize the target speech signal. The parallel exemplars (dictionary) consist of the source exemplars and target exemplars, having the same texts uttered by the source and target speakers. The input source signal is decomposed into the source exemplars, noise exemplars obtained from the input signal, and their weights (activities). Then, by using the weights of the source exemplars, the converted signal is constructed from the target exemplars. We carried out speaker conversion tasks using clean speech data and noise-added speech data. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based method.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"48 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120909672","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424271
Deana Pennell, Yang Liu
Abbreviations in informal text, and research efforts to expand them to the standard English words from which they were derived, have become increasingly common. These methods are almost solely evaluated using the final word error rate (WER) after normalization; however, this metric may not be reasonable for a text-to-speech (TTS) system where words may be pronounced correctly despite being misspelled. This paper shows that normalization of informal text improves the output of TTS not only in terms of WER but also in terms of phoneme error rate (PER) and human perceptual experiments.
{"title":"Evaluating the effect of normalizing informal text on TTS output","authors":"Deana Pennell, Yang Liu","doi":"10.1109/SLT.2012.6424271","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424271","url":null,"abstract":"Abbreviations in informal text, and research efforts to expand them to the standard English words from which they were derived, have become increasingly common. These methods are almost solely evaluated using the final word error rate (WER) after normalization; however, this metric may not be reasonable for a text-to-speech (TTS) system where words may be pronounced correctly despite being misspelled. This paper shows that normalization of informal text improves the output of TTS not only in terms of WER but also in terms of phoneme error rate (PER) and human perceptual experiments.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116980892","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424228
Tomas Mikolov, G. Zweig
Recurrent neural network language models (RNNLMs) have recently demonstrated state-of-the-art performance across a variety of tasks. In this paper, we improve their performance by providing a contextual real-valued input vector in association with each word. This vector is used to convey contextual information about the sentence being modeled. By performing Latent Dirichlet Allocation using a block of preceding text, we achieve a topic-conditioned RNNLM. This approach has the key advantage of avoiding the data fragmentation associated with building multiple topic models on different data subsets. We report perplexity results on the Penn Treebank data, where we achieve a new state-of-the-art. We further apply the model to the Wall Street Journal speech recognition task, where we observe improvements in word-error-rate.
{"title":"Context dependent recurrent neural network language model","authors":"Tomas Mikolov, G. Zweig","doi":"10.1109/SLT.2012.6424228","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424228","url":null,"abstract":"Recurrent neural network language models (RNNLMs) have recently demonstrated state-of-the-art performance across a variety of tasks. In this paper, we improve their performance by providing a contextual real-valued input vector in association with each word. This vector is used to convey contextual information about the sentence being modeled. By performing Latent Dirichlet Allocation using a block of preceding text, we achieve a topic-conditioned RNNLM. This approach has the key advantage of avoiding the data fragmentation associated with building multiple topic models on different data subsets. We report perplexity results on the Penn Treebank data, where we achieve a new state-of-the-art. We further apply the model to the Wall Street Journal speech recognition task, where we observe improvements in word-error-rate.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116447943","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 : 2012-12-01DOI: 10.1109/SLT.2012.6424225
Asli Celikyilmaz, Dilek Z. Hakkani-Tür, Gökhan Tür
In natural language human-machine statistical dialog systems, semantic interpretation is a key task typically performed following semantic parsing, and aims to extract canonical meaning representations of semantic components. In the literature, usually manually built rules are used for this task, even for implicitly mentioned non-named semantic components (like genre of a movie or price range of a restaurant). In this study, we present statistical methods for modeling interpretation, which can also benefit from semantic features extracted from large in-domain knowledge sources. We extract features from user utterances using a semantic parser and additional semantic features from textual sources (online reviews, synopses, etc.) using a novel tree clustering approach, to represent unstructured information that correspond to implicit semantic components related to targeted slots in the user's utterances. We evaluate our models on a virtual personal assistance system and demonstrate that our interpreter is effective in that it does not only improve the utterance interpretation in spoken dialog systems (reducing the interpretation error rate by 36% relative compared to a language model baseline), but also unveils hidden semantic units that are otherwise nearly impossible to extract from purely manual lexical features that are typically used in utterance interpretation.
{"title":"Statistical semantic interpretation modeling for spoken language understanding with enriched semantic features","authors":"Asli Celikyilmaz, Dilek Z. Hakkani-Tür, Gökhan Tür","doi":"10.1109/SLT.2012.6424225","DOIUrl":"https://doi.org/10.1109/SLT.2012.6424225","url":null,"abstract":"In natural language human-machine statistical dialog systems, semantic interpretation is a key task typically performed following semantic parsing, and aims to extract canonical meaning representations of semantic components. In the literature, usually manually built rules are used for this task, even for implicitly mentioned non-named semantic components (like genre of a movie or price range of a restaurant). In this study, we present statistical methods for modeling interpretation, which can also benefit from semantic features extracted from large in-domain knowledge sources. We extract features from user utterances using a semantic parser and additional semantic features from textual sources (online reviews, synopses, etc.) using a novel tree clustering approach, to represent unstructured information that correspond to implicit semantic components related to targeted slots in the user's utterances. We evaluate our models on a virtual personal assistance system and demonstrate that our interpreter is effective in that it does not only improve the utterance interpretation in spoken dialog systems (reducing the interpretation error rate by 36% relative compared to a language model baseline), but also unveils hidden semantic units that are otherwise nearly impossible to extract from purely manual lexical features that are typically used in utterance interpretation.","PeriodicalId":375378,"journal":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126812238","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：