Weicheng Zhang, Cheng-chieh Yeh, Will Beckman, T. Raitio, Ramya Rasipuram, L. Golipour, David Winarsky
Despite recent advances in text-to-speech (TTS) technology, auto-narration of long-form content such as books remains a challenge. The goal of this work is to enhance neural TTS to be suitable for long-form content such as audiobooks. In addition to high quality, we aim to provide a compelling and engaging listening experience with expressivity that spans beyond a single sentence to a paragraph level so that the user can not only follow the story but also enjoy listening to it. Towards that goal, we made four enhancements to our baseline TTS system: incorporation of BERT embeddings, explicit prosody prediction from text, long-context modeling over multiple sentences, and pre-training on long-form data. We propose an evaluation framework tailored to long-form content that evaluates the synthesis on segments spanning multiple paragraphs and focuses on elements such as comprehension, ease of listening, ability to keep attention, and enjoyment. The evaluation results show that the proposed approach outperforms the baseline on all evaluated metrics, with an absolute 0.47 MOS gain in overall quality. Ablation studies further confirm the effectiveness of the proposed enhancements.
{"title":"Audiobook synthesis with long-form neural text-to-speech","authors":"Weicheng Zhang, Cheng-chieh Yeh, Will Beckman, T. Raitio, Ramya Rasipuram, L. Golipour, David Winarsky","doi":"10.21437/ssw.2023-22","DOIUrl":"https://doi.org/10.21437/ssw.2023-22","url":null,"abstract":"Despite recent advances in text-to-speech (TTS) technology, auto-narration of long-form content such as books remains a challenge. The goal of this work is to enhance neural TTS to be suitable for long-form content such as audiobooks. In addition to high quality, we aim to provide a compelling and engaging listening experience with expressivity that spans beyond a single sentence to a paragraph level so that the user can not only follow the story but also enjoy listening to it. Towards that goal, we made four enhancements to our baseline TTS system: incorporation of BERT embeddings, explicit prosody prediction from text, long-context modeling over multiple sentences, and pre-training on long-form data. We propose an evaluation framework tailored to long-form content that evaluates the synthesis on segments spanning multiple paragraphs and focuses on elements such as comprehension, ease of listening, ability to keep attention, and enjoyment. The evaluation results show that the proposed approach outperforms the baseline on all evaluated metrics, with an absolute 0.47 MOS gain in overall quality. Ablation studies further confirm the effectiveness of the proposed enhancements.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122861468","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}
We propose a new method to adaptively modify the rhythm of a given speech signal. We train a masked convolutional encoder-decoder network to generate this attention map via a stochastic version of the mean absolute error loss function. Our model also predicts the length of the target speech signal using the encoder embeddings, which determines the number of time steps for the decoding operation. During testing, we use the learned attention map as a proxy for the frame-wise similarity matrix between the given input speech and an unknown target speech signal. In an open-loop fashion, we compute a warping path for rhythm modification. Our experiments demonstrate that this adaptive framework achieves similar performance as the fully supervised dynamic time warping algorithm on both voice conversion and emotion conversion tasks. We also show that the modified speech utterances achieve high user quality ratings, thus highlighting the practical utility of our method.
{"title":"Adaptive Duration Modification of Speech using Masked Convolutional Networks and Open-Loop Time Warping","authors":"Ravi Shankar, Archana Venkataraman","doi":"10.21437/ssw.2023-28","DOIUrl":"https://doi.org/10.21437/ssw.2023-28","url":null,"abstract":"We propose a new method to adaptively modify the rhythm of a given speech signal. We train a masked convolutional encoder-decoder network to generate this attention map via a stochastic version of the mean absolute error loss function. Our model also predicts the length of the target speech signal using the encoder embeddings, which determines the number of time steps for the decoding operation. During testing, we use the learned attention map as a proxy for the frame-wise similarity matrix between the given input speech and an unknown target speech signal. In an open-loop fashion, we compute a warping path for rhythm modification. Our experiments demonstrate that this adaptive framework achieves similar performance as the fully supervised dynamic time warping algorithm on both voice conversion and emotion conversion tasks. We also show that the modified speech utterances achieve high user quality ratings, thus highlighting the practical utility of our method.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"279 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122768349","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}
Text-To-Speech (TTS) systems are commonly evaluated along two main dimensions: intelligibility and naturalness. While there are clear proxies for intelligibility measurements such as transcription Word-Error-Rate (WER), naturalness is not nearly so well defined. In this paper, we present the results of our attempt to learn what aspects human listeners consider when they are asked to evaluate the “naturalness” of TTS systems. We conducted a user study similar to common TTS evaluations and at the end asked the subject to define the sense of naturalness that they had used. Then we coded their answers and statistically analysed the distribution of codes to create a list of aspects that users consider as part of naturalness. We can now provide a list of suggested replacement questions to use instead of a single oblique notion of naturalness.
{"title":"Better Replacement for TTS Naturalness Evaluation","authors":"S. Shirali-Shahreza, Gerald Penn","doi":"10.21437/ssw.2023-31","DOIUrl":"https://doi.org/10.21437/ssw.2023-31","url":null,"abstract":"Text-To-Speech (TTS) systems are commonly evaluated along two main dimensions: intelligibility and naturalness. While there are clear proxies for intelligibility measurements such as transcription Word-Error-Rate (WER), naturalness is not nearly so well defined. In this paper, we present the results of our attempt to learn what aspects human listeners consider when they are asked to evaluate the “naturalness” of TTS systems. We conducted a user study similar to common TTS evaluations and at the end asked the subject to define the sense of naturalness that they had used. Then we coded their answers and statistically analysed the distribution of codes to create a list of aspects that users consider as part of naturalness. We can now provide a list of suggested replacement questions to use instead of a single oblique notion of naturalness.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125866015","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}
G. Bailly, Martin Lenglet, O. Perrotin, E. Klabbers
{"title":"Advocating for text input in multi-speaker text-to-speech systems","authors":"G. Bailly, Martin Lenglet, O. Perrotin, E. Klabbers","doi":"10.21437/ssw.2023-1","DOIUrl":"https://doi.org/10.21437/ssw.2023-1","url":null,"abstract":"","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127568201","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}
Takenori Yoshimura, Takato Fujimoto, Keiichiro Oura, K. Tokuda
The Speech Signal Processing ToolKit (SPTK) is an open-source suite of speech signal processing tools, which has been developed and maintained by the SPTK working group and has widely contributed to the speech signal processing community since 1998. Although SPTK has reached over a hundred thousand downloads, the concepts as well as the features have not yet been widely disseminated. This paper gives an overview of SPTK and demonstrations to provide a better understanding of the toolkit. We have recently developed its differentiable Py-Torch version, diffsptk , to adapt to advancements in the deep learning field. The details of diffsptk are also presented in this paper. We hope that the toolkit will help developers and researchers working in the field of speech signal processing.
{"title":"SPTK4: An Open-Source Software Toolkit for Speech Signal Processing","authors":"Takenori Yoshimura, Takato Fujimoto, Keiichiro Oura, K. Tokuda","doi":"10.21437/ssw.2023-33","DOIUrl":"https://doi.org/10.21437/ssw.2023-33","url":null,"abstract":"The Speech Signal Processing ToolKit (SPTK) is an open-source suite of speech signal processing tools, which has been developed and maintained by the SPTK working group and has widely contributed to the speech signal processing community since 1998. Although SPTK has reached over a hundred thousand downloads, the concepts as well as the features have not yet been widely disseminated. This paper gives an overview of SPTK and demonstrations to provide a better understanding of the toolkit. We have recently developed its differentiable Py-Torch version, diffsptk , to adapt to advancements in the deep learning field. The details of diffsptk are also presented in this paper. We hope that the toolkit will help developers and researchers working in the field of speech signal processing.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133680724","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}
Ensuring accurate pronunciation is critical for high-quality text-to-speech (TTS). This typically requires a phoneme-based pro-nunciation dictionary, which is labour-intensive and costly to create. Previous work has suggested using graphemes instead of phonemes, but the inevitable pronunciation errors that occur cannot be fixed, since there is no longer a pronunciation dictionary. As an alternative, speech-based self-supervised learning (SSL) models have been proposed for pronunciation control, but these models are computationally expensive to train, produce representations that are not easily interpretable, and capture unwanted non-phonemic information. To address these limitations, we propose Spell4TTS, a novel method that generates acoustically-informed word spellings. Spellings are both inter-pretable and easily edited. The method could be applied to any existing pre-built TTS system. Our experiments show that the method creates word spellings that lead to fewer TTS pronunciation errors than the original spellings, or an Automatic Speech Recognition baseline. Additionally, we observe that pronunciation can be further enhanced by ranking candidates in the space of SSL speech representations, and by incorporating Human-in-the-Loop screening over the top-ranked spellings devised by our method. By working with spellings of words (composed of characters), the method lowers the entry barrier for TTS sys-tem development for languages with limited pronunciation resources. It should reduce the time and cost involved in creating and maintaining pronunciation dictionaries.
{"title":"Spell4TTS: Acoustically-informed spellings for improving text-to-speech pronunciations","authors":"Jason Fong, Hao Tang, Simon King","doi":"10.21437/ssw.2023-2","DOIUrl":"https://doi.org/10.21437/ssw.2023-2","url":null,"abstract":"Ensuring accurate pronunciation is critical for high-quality text-to-speech (TTS). This typically requires a phoneme-based pro-nunciation dictionary, which is labour-intensive and costly to create. Previous work has suggested using graphemes instead of phonemes, but the inevitable pronunciation errors that occur cannot be fixed, since there is no longer a pronunciation dictionary. As an alternative, speech-based self-supervised learning (SSL) models have been proposed for pronunciation control, but these models are computationally expensive to train, produce representations that are not easily interpretable, and capture unwanted non-phonemic information. To address these limitations, we propose Spell4TTS, a novel method that generates acoustically-informed word spellings. Spellings are both inter-pretable and easily edited. The method could be applied to any existing pre-built TTS system. Our experiments show that the method creates word spellings that lead to fewer TTS pronunciation errors than the original spellings, or an Automatic Speech Recognition baseline. Additionally, we observe that pronunciation can be further enhanced by ranking candidates in the space of SSL speech representations, and by incorporating Human-in-the-Loop screening over the top-ranked spellings devised by our method. By working with spellings of words (composed of characters), the method lowers the entry barrier for TTS sys-tem development for languages with limited pronunciation resources. It should reduce the time and cost involved in creating and maintaining pronunciation dictionaries.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132536684","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}
This paper describes a novel approach to non-parallel many-to-many voice conversion (VC) that utilizes a variant of the conditional variational autoencoder (VAE) called a perturbation-resistant VAE (PRVAE). In VAE-based VC, it is commonly assumed that the encoder extracts content from the input speech while removing source speaker information. Following this extraction, the decoder generates output from the extracted content and target speaker information. However, in practice, the encoded features may still retain source speaker information, which can lead to a degradation of speech quality during speaker conversion tasks. To address this issue, we propose a perturbation-resistant encoder trained to match the encoded features of the input speech with those of a pseudo-speech generated through a content-preserving transformation of the input speech’s fundamental frequency and spectral envelope using a combination of pure signal processing techniques. Our experimental results demonstrate that this straightforward constraint significantly enhances the performance in non-parallel many-to-many speaker conversion tasks. Audio samples can be accessed at our webpage 1 .
{"title":"PRVAE-VC: Non-Parallel Many-to-Many Voice Conversion with Perturbation-Resistant Variational Autoencoder","authors":"Kou Tanaka, H. Kameoka, Takuhiro Kaneko","doi":"10.21437/ssw.2023-14","DOIUrl":"https://doi.org/10.21437/ssw.2023-14","url":null,"abstract":"This paper describes a novel approach to non-parallel many-to-many voice conversion (VC) that utilizes a variant of the conditional variational autoencoder (VAE) called a perturbation-resistant VAE (PRVAE). In VAE-based VC, it is commonly assumed that the encoder extracts content from the input speech while removing source speaker information. Following this extraction, the decoder generates output from the extracted content and target speaker information. However, in practice, the encoded features may still retain source speaker information, which can lead to a degradation of speech quality during speaker conversion tasks. To address this issue, we propose a perturbation-resistant encoder trained to match the encoded features of the input speech with those of a pseudo-speech generated through a content-preserving transformation of the input speech’s fundamental frequency and spectral envelope using a combination of pure signal processing techniques. Our experimental results demonstrate that this straightforward constraint significantly enhances the performance in non-parallel many-to-many speaker conversion tasks. Audio samples can be accessed at our webpage 1 .","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128169759","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}
The Mean Opinion Score (MOS) is a prevalent metric in TTS evaluation. Although standards for collecting and reporting MOS exist, researchers seem to use the term inconsistently, and underreport the details of their testing methodologies. A survey of Interspeech and SSW papers from 2021-2022 shows that most authors do not report scale labels, increments, or instructions to participants, and those who do diverge in terms of their implementation. It is also unclear in many cases whether listeners were asked to rate naturalness, or overall quality. MOS obtained for natural speech using different testing methodologies vary in the surveyed papers: specifically, quality MOS is on average higher than naturalness MOS. We carried out several listening tests using the same stimuli but with differences in the scale increment and instructions about what participants should rate, and found that both of these variables affected MOS for some systems.
{"title":"Stuck in the MOS pit: A critical analysis of MOS test methodology in TTS evaluation","authors":"Ambika Kirkland, Shivam Mehta, Harm Lameris, G. Henter, Éva Székely, Joakim Gustafson","doi":"10.21437/ssw.2023-7","DOIUrl":"https://doi.org/10.21437/ssw.2023-7","url":null,"abstract":"The Mean Opinion Score (MOS) is a prevalent metric in TTS evaluation. Although standards for collecting and reporting MOS exist, researchers seem to use the term inconsistently, and underreport the details of their testing methodologies. A survey of Interspeech and SSW papers from 2021-2022 shows that most authors do not report scale labels, increments, or instructions to participants, and those who do diverge in terms of their implementation. It is also unclear in many cases whether listeners were asked to rate naturalness, or overall quality. MOS obtained for natural speech using different testing methodologies vary in the surveyed papers: specifically, quality MOS is on average higher than naturalness MOS. We carried out several listening tests using the same stimuli but with differences in the scale increment and instructions about what participants should rate, and found that both of these variables affected MOS for some systems.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125232081","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}
As speech synthesis quality reaches high levels of naturalness for isolated utterances, more work is focusing on the synthesis of context-dependent conversational speech. The role of context in conversation is still poorly understood and many contextual factors can affect an utterances’s prosodic realisation. Most studies incorporating context use rich acoustic or textual embeddings of the previous context, then demonstrate improvements in overall naturalness. Such studies are not informative about what the context embedding represents, or how it affects an utterance’s realisation. So instead, we narrow the focus to a single, explicit contextual factor. In the current work, this is turn-taking. We condition a speech synthesis model on whether an utterance is turn-final. Objective measures and targeted subjective evaluation are used to demonstrate that the model can synthesise turn-taking cues which are perceived by listeners, with results being speaker-dependent.
{"title":"Synthesising turn-taking cues using natural conversational data","authors":"Johannah O'Mahony, Catherine Lai, Simon King","doi":"10.21437/ssw.2023-12","DOIUrl":"https://doi.org/10.21437/ssw.2023-12","url":null,"abstract":"As speech synthesis quality reaches high levels of naturalness for isolated utterances, more work is focusing on the synthesis of context-dependent conversational speech. The role of context in conversation is still poorly understood and many contextual factors can affect an utterances’s prosodic realisation. Most studies incorporating context use rich acoustic or textual embeddings of the previous context, then demonstrate improvements in overall naturalness. Such studies are not informative about what the context embedding represents, or how it affects an utterance’s realisation. So instead, we narrow the focus to a single, explicit contextual factor. In the current work, this is turn-taking. We condition a speech synthesis model on whether an utterance is turn-final. Objective measures and targeted subjective evaluation are used to demonstrate that the model can synthesise turn-taking cues which are perceived by listeners, with results being speaker-dependent.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120967024","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}
Fritz Seebauer, Michael Kuhlmann, Reinhold Haeb-Umbach, P. Wagner
The aim of this paper is to generate a more comprehensive framework for evaluating synthetic speech. To this end, a line of tests resulting in an exploratory factor analysis (EFA) have been carried out. The proposed dimensions that encapsulate the construct of “synthetic speech quality” are: “human-likeness”, “audio quality”, “negative emotion”, “dominance”, “positive emotion”, “calmness”, “seniority” and “gender”, with item-to-total correlations pointing towards “gender” being an orthogonal construct. A subsequent analysis on common acoustic features, found in forensic and phonetic literature, reveals very weak correlations with the proposed scales. Inter-rater and inter-item agreement measures additionally reveal low consistency within the scales. We also make the case that there is a need for a more fine grained approach when investigating the quality of synthetic speech systems, and propose a method that attempts to capture individual quality dimensions in the time domain.
{"title":"Re-examining the quality dimensions of synthetic speech","authors":"Fritz Seebauer, Michael Kuhlmann, Reinhold Haeb-Umbach, P. Wagner","doi":"10.21437/ssw.2023-6","DOIUrl":"https://doi.org/10.21437/ssw.2023-6","url":null,"abstract":"The aim of this paper is to generate a more comprehensive framework for evaluating synthetic speech. To this end, a line of tests resulting in an exploratory factor analysis (EFA) have been carried out. The proposed dimensions that encapsulate the construct of “synthetic speech quality” are: “human-likeness”, “audio quality”, “negative emotion”, “dominance”, “positive emotion”, “calmness”, “seniority” and “gender”, with item-to-total correlations pointing towards “gender” being an orthogonal construct. A subsequent analysis on common acoustic features, found in forensic and phonetic literature, reveals very weak correlations with the proposed scales. Inter-rater and inter-item agreement measures additionally reveal low consistency within the scales. We also make the case that there is a need for a more fine grained approach when investigating the quality of synthetic speech systems, and propose a method that attempts to capture individual quality dimensions in the time domain.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115965443","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：