Pub Date : 2011-12-01DOI: 10.1109/ASRU.2011.6163986
Zixing Zhang, F. Weninger, M. Wöllmer, Björn Schuller
One of the ever-present bottlenecks in Automatic Emotion Recognition is data sparseness. We therefore investigate the suitability of unsupervised learning in cross-corpus acoustic emotion recognition through a large-scale study with six commonly used databases, including acted and natural emotion speech, and covering a variety of application scenarios and acoustic conditions. We show that adding unlabeled emotional speech to agglomerated multi-corpus training sets can enhance recognition performance even in a challenging cross-corpus setting; furthermore, we show that the expected gain by adding unlabeled data on average is approximately half the one achieved by additional manually labeled data in leave-one-corpus-out validation.
{"title":"Unsupervised learning in cross-corpus acoustic emotion recognition","authors":"Zixing Zhang, F. Weninger, M. Wöllmer, Björn Schuller","doi":"10.1109/ASRU.2011.6163986","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163986","url":null,"abstract":"One of the ever-present bottlenecks in Automatic Emotion Recognition is data sparseness. We therefore investigate the suitability of unsupervised learning in cross-corpus acoustic emotion recognition through a large-scale study with six commonly used databases, including acted and natural emotion speech, and covering a variety of application scenarios and acoustic conditions. We show that adding unlabeled emotional speech to agglomerated multi-corpus training sets can enhance recognition performance even in a challenging cross-corpus setting; furthermore, we show that the expected gain by adding unlabeled data on average is approximately half the one achieved by additional manually labeled data in leave-one-corpus-out validation.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129858631","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163979
Emily Tucker Prud'hommeaux, Brian Roark
Narrative recall tasks are commonly included in neurological examinations, as deficits in narrative memory are associated with disorders such as Alzheimer's dementia. We explore methods for automatically scoring narrative retellings via alignment to a source narrative. Standard alignment methods, designed for large bilingual corpora for machine translation, yield high alignment error rates (AER) on our small monolingual corpora. We present modifications to these methods that obtain a decrease in AER, an increase in scoring accuracy, and diagnostic classification performance comparable to that of manual methods, thus demonstrating the utility of these techniques for this task and other tasks relying on monolingual alignments.
{"title":"Alignment of spoken narratives for automated neuropsychological assessment","authors":"Emily Tucker Prud'hommeaux, Brian Roark","doi":"10.1109/ASRU.2011.6163979","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163979","url":null,"abstract":"Narrative recall tasks are commonly included in neurological examinations, as deficits in narrative memory are associated with disorders such as Alzheimer's dementia. We explore methods for automatically scoring narrative retellings via alignment to a source narrative. Standard alignment methods, designed for large bilingual corpora for machine translation, yield high alignment error rates (AER) on our small monolingual corpora. We present modifications to these methods that obtain a decrease in AER, an increase in scoring accuracy, and diagnostic classification performance comparable to that of manual methods, thus demonstrating the utility of these techniques for this task and other tasks relying on monolingual alignments.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129869419","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163932
H. Kuo, E. Arisoy, L. Mangu, G. Saon
In this paper we explore discriminative language modeling (DLM) on highly optimized state-of-the-art large vocabulary Arabic broadcast speech recognition systems used for the Phase 5 DARPA GALE Evaluation. In particular, we study in detail a minimum Bayes risk (MBR) criterion for DLM. MBR training outperforms perceptron training. Interestingly, we found that our DLMs generalized to mismatched conditions, such as using a different acoustic model during testing. We also examine the interesting problem of unsupervised DLM training using a Bayes risk metric as a surrogate for word error rate (WER). In some experiments, we were able to obtain about half of the gain of the supervised DLM.
{"title":"Minimum Bayes risk discriminative language models for Arabic speech recognition","authors":"H. Kuo, E. Arisoy, L. Mangu, G. Saon","doi":"10.1109/ASRU.2011.6163932","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163932","url":null,"abstract":"In this paper we explore discriminative language modeling (DLM) on highly optimized state-of-the-art large vocabulary Arabic broadcast speech recognition systems used for the Phase 5 DARPA GALE Evaluation. In particular, we study in detail a minimum Bayes risk (MBR) criterion for DLM. MBR training outperforms perceptron training. Interestingly, we found that our DLMs generalized to mismatched conditions, such as using a different acoustic model during testing. We also examine the interesting problem of unsupervised DLM training using a Bayes risk metric as a surrogate for word error rate (WER). In some experiments, we were able to obtain about half of the gain of the supervised DLM.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131212292","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163940
Timo Mertens, Kit Thambiratnam, F. Seide
We investigate automatic pronunciation adaptation for non-native accented speech by using statistical models trained on multi-span lingustic parse tables to generate candidate mispronunciations for a target language. Compared to traditional phone re-writing rules, parse table modeling captures more context in the form of phone-clusters or syllables, and encodes abstract features such as word-internal position or syllable structure. The proposed approach is attractive because it gives a unified method for combining multiple levels of linguistic information. The reported experiments demonstrate word error rate reductions of up to 7.9% and 3.3% absolute on Italian and German accented English using lexicon adaptation alone, and 12.4% and 11.3% absolute when combined with acoustic adaptation.
{"title":"Subword-based multi-span pronunciation adaptation for recognizing accented speech","authors":"Timo Mertens, Kit Thambiratnam, F. Seide","doi":"10.1109/ASRU.2011.6163940","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163940","url":null,"abstract":"We investigate automatic pronunciation adaptation for non-native accented speech by using statistical models trained on multi-span lingustic parse tables to generate candidate mispronunciations for a target language. Compared to traditional phone re-writing rules, parse table modeling captures more context in the form of phone-clusters or syllables, and encodes abstract features such as word-internal position or syllable structure. The proposed approach is attractive because it gives a unified method for combining multiple levels of linguistic information. The reported experiments demonstrate word error rate reductions of up to 7.9% and 3.3% absolute on Italian and German accented English using lexicon adaptation alone, and 12.4% and 11.3% absolute when combined with acoustic adaptation.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131708679","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163953
Ryuichiro Higashinaka, N. Kawamae, Kugatsu Sadamitsu, Yasuhiro Minami, Toyomi Meguro, Kohji Dohsaka, H. Inagaki
The current problem in building a conversational model from Twitter data is the scarcity of long conversations. According to our statistics, more than 90% of conversations in Twitter are composed of just two tweets. Previous work has utilized only conversations lasting longer than three tweets for dialogue modeling so that more than a single interaction can be successfully modeled. This paper verifies, by experiment, that two-tweet exchanges alone can lead to conversational models that are comparable to those made from longer-tweet conversations. This finding leverages the value of Twitter as a dialogue corpus and opens the possibility of better conversational modeling using Twitter data.
{"title":"Building a conversational model from two-tweets","authors":"Ryuichiro Higashinaka, N. Kawamae, Kugatsu Sadamitsu, Yasuhiro Minami, Toyomi Meguro, Kohji Dohsaka, H. Inagaki","doi":"10.1109/ASRU.2011.6163953","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163953","url":null,"abstract":"The current problem in building a conversational model from Twitter data is the scarcity of long conversations. According to our statistics, more than 90% of conversations in Twitter are composed of just two tweets. Previous work has utilized only conversations lasting longer than three tweets for dialogue modeling so that more than a single interaction can be successfully modeled. This paper verifies, by experiment, that two-tweet exchanges alone can lead to conversational models that are comparable to those made from longer-tweet conversations. This finding leverages the value of Twitter as a dialogue corpus and opens the possibility of better conversational modeling using Twitter data.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123143684","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163939
U. Chaudhari, Xiaodong Cui, Bowen Zhou, Rong Zhang
In this paper, we study the issue of generating pronunciations for training and decoding with an ASR system for Pashto in the context of a Speech to Speech Translation system developed for TRANSTAC. As with other low resourced languages, a limited amount of acoustic training data was available with a corresponding set of manually produced vowelized pronunciations. We augment this data with other sources, but lack pronunciations for unseen words in the new audio and associated text. Four methods are investigated for generating these pronunciations, or baseforms: an heuristic grapheme to phoneme map, manual annotation, and two methods based on statistical models. The first of these uses a joint Maximum Entropy N-gram model while the other is based on a log-linear Statistical Machine Translation model. We report results on a state of the art, discriminatively trained, ASR system and show that the manual and statistical methods provide an improvement over the grapheme to phoneme map. Moreover, we demonstrate that the automatic statistical methods can perform as well or better than manual generation by native speakers, even in the case where we have a significant number of high quality, manually generated pronunciations beyond those provided by the TRANSTAC program.
{"title":"An investigation of heuristic, manual and statistical pronunciation derivation for Pashto","authors":"U. Chaudhari, Xiaodong Cui, Bowen Zhou, Rong Zhang","doi":"10.1109/ASRU.2011.6163939","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163939","url":null,"abstract":"In this paper, we study the issue of generating pronunciations for training and decoding with an ASR system for Pashto in the context of a Speech to Speech Translation system developed for TRANSTAC. As with other low resourced languages, a limited amount of acoustic training data was available with a corresponding set of manually produced vowelized pronunciations. We augment this data with other sources, but lack pronunciations for unseen words in the new audio and associated text. Four methods are investigated for generating these pronunciations, or baseforms: an heuristic grapheme to phoneme map, manual annotation, and two methods based on statistical models. The first of these uses a joint Maximum Entropy N-gram model while the other is based on a log-linear Statistical Machine Translation model. We report results on a state of the art, discriminatively trained, ASR system and show that the manual and statistical methods provide an improvement over the grapheme to phoneme map. Moreover, we demonstrate that the automatic statistical methods can perform as well or better than manual generation by native speakers, even in the case where we have a significant number of high quality, manually generated pronunciations beyond those provided by the TRANSTAC program.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123147261","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163902
M. Wöllmer, Björn Schuller, G. Rigoll
We present a novel automatic speech recognition (ASR) front-end that unites Long Short-Term Memory context modeling, bidirectional speech processing, and bottleneck (BN) networks for enhanced Tandem speech feature generation. Bidirectional Long Short-Term Memory (BLSTM) networks were shown to be well suited for phoneme recognition and probabilistic feature extraction since they efficiently incorporate a flexible amount of long-range temporal context, leading to better ASR results than conventional recurrent networks or multi-layer perceptrons. Combining BLSTM modeling and bottleneck feature generation allows us to produce feature vectors of arbitrary size, independent of the network training targets. Experiments on the COSINE and the Buckeye corpora containing spontaneous, conversational speech show that the proposed BN-BLSTM front-end leads to better ASR accuracies than previously proposed BLSTM-based Tandem and multi-stream systems.
{"title":"A novel bottleneck-BLSTM front-end for feature-level context modeling in conversational speech recognition","authors":"M. Wöllmer, Björn Schuller, G. Rigoll","doi":"10.1109/ASRU.2011.6163902","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163902","url":null,"abstract":"We present a novel automatic speech recognition (ASR) front-end that unites Long Short-Term Memory context modeling, bidirectional speech processing, and bottleneck (BN) networks for enhanced Tandem speech feature generation. Bidirectional Long Short-Term Memory (BLSTM) networks were shown to be well suited for phoneme recognition and probabilistic feature extraction since they efficiently incorporate a flexible amount of long-range temporal context, leading to better ASR results than conventional recurrent networks or multi-layer perceptrons. Combining BLSTM modeling and bottleneck feature generation allows us to produce feature vectors of arbitrary size, independent of the network training targets. Experiments on the COSINE and the Buckeye corpora containing spontaneous, conversational speech show that the proposed BN-BLSTM front-end leads to better ASR accuracies than previously proposed BLSTM-based Tandem and multi-stream systems.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121850096","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163917
R. V. Dalen, M. Gales
Model compensation methods for noise-robust speech recognition have shown good performance. Predictive linear transformations can approximate these methods to balance computational complexity and compensation accuracy. This paper examines both of these approaches from a variational perspective. Using a matched-pair approximation at the component level yields a number of standard forms of model compensation and predictive linear transformations. However, a tighter bound can be obtained by using variational approximations at the state level. Both model-based and predictive linear transform schemes can be implemented in this framework. Preliminary results show that the tighter bound obtained from the state-level variational approach can yield improved performance over standard schemes.
{"title":"A variational perspective on noise-robust speech recognition","authors":"R. V. Dalen, M. Gales","doi":"10.1109/ASRU.2011.6163917","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163917","url":null,"abstract":"Model compensation methods for noise-robust speech recognition have shown good performance. Predictive linear transformations can approximate these methods to balance computational complexity and compensation accuracy. This paper examines both of these approaches from a variational perspective. Using a matched-pair approximation at the component level yields a number of standard forms of model compensation and predictive linear transformations. However, a tighter bound can be obtained by using variational approximations at the state level. Both model-based and predictive linear transform schemes can be implemented in this framework. Preliminary results show that the tighter bound obtained from the state-level variational approach can yield improved performance over standard schemes.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123994689","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163941
H. Cucu, L. Besacier, C. Burileanu, Andi Buzo
This study investigates the use of machine translated text for ASR domain adaptation. The proposed methodology is applicable when domain-specific data is available in language X only, whereas the goal is to develop a domain-specific system in language Y. Two semi-supervised methods are introduced and compared with a fully unsupervised approach, which represents the baseline. While both unsupervised and semi-supervised approaches allow to quickly develop an accurate domain-specific ASR system, the semi-supervised approaches overpass the unsupervised one by 10% to 29% relative, depending on the amount of human post-processed data available. An in-depth analysis, to explain how the machine translated text improves the performance of the domain-specific ASR, is also given at the end of this paper.
{"title":"Investigating the role of machine translated text in ASR domain adaptation: Unsupervised and semi-supervised methods","authors":"H. Cucu, L. Besacier, C. Burileanu, Andi Buzo","doi":"10.1109/ASRU.2011.6163941","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163941","url":null,"abstract":"This study investigates the use of machine translated text for ASR domain adaptation. The proposed methodology is applicable when domain-specific data is available in language X only, whereas the goal is to develop a domain-specific system in language Y. Two semi-supervised methods are introduced and compared with a fully unsupervised approach, which represents the baseline. While both unsupervised and semi-supervised approaches allow to quickly develop an accurate domain-specific ASR system, the semi-supervised approaches overpass the unsupervised one by 10% to 29% relative, depending on the amount of human post-processed data available. An in-depth analysis, to explain how the machine translated text improves the performance of the domain-specific ASR, is also given at the end of this paper.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115951310","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 : 2011-12-01DOI: 10.1109/ASRU.2011.6163951
Toyomi Meguro, Yasuhiro Minami, Ryuichiro Higashinaka, Kohji Dohsaka
We have been working on dialogue control for listening agents. In our previous study [1], we proposed a dialogue control method that maximizes user satisfaction using partially observable Markov decision processes (POMDPs) and evaluated it by a dialogue simulation. We found that it significantly outperforms other stochastic dialogue control methods. However, this result does not necessarily mean that our method works as well in real dialogues with human users. Therefore, in this paper, we evaluate our dialogue control method by a Wizard of Oz (WoZ) experiment. The experimental results show that our POMDP-based method achieves significantly higher user satisfaction than other stochastic models, confirming the validity of our approach. This paper is the first to show the usefulness of POMDP-based dialogue control using human users when the target function is to maximize user satisfaction.
{"title":"Wizard of Oz evaluation of listening-oriented dialogue control using POMDP","authors":"Toyomi Meguro, Yasuhiro Minami, Ryuichiro Higashinaka, Kohji Dohsaka","doi":"10.1109/ASRU.2011.6163951","DOIUrl":"https://doi.org/10.1109/ASRU.2011.6163951","url":null,"abstract":"We have been working on dialogue control for listening agents. In our previous study [1], we proposed a dialogue control method that maximizes user satisfaction using partially observable Markov decision processes (POMDPs) and evaluated it by a dialogue simulation. We found that it significantly outperforms other stochastic dialogue control methods. However, this result does not necessarily mean that our method works as well in real dialogues with human users. Therefore, in this paper, we evaluate our dialogue control method by a Wizard of Oz (WoZ) experiment. The experimental results show that our POMDP-based method achieves significantly higher user satisfaction than other stochastic models, confirming the validity of our approach. This paper is the first to show the usefulness of POMDP-based dialogue control using human users when the target function is to maximize user satisfaction.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127370493","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：