发布求助
文献互助 智能选刊 最新文献

2022 IEEE Spoken Language Technology Workshop (SLT)最新文献

筛选
英文 中文
A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning 说话人表征学习的自监督蒸馏综合研究
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-28 DOI: 10.1109/SLT54892.2023.10022470
Zhengyang Chen, Yao Qian, Bing Han, Y. Qian, Michael Zeng
{"title":"A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning","authors":"Zhengyang Chen, Yao Qian, Bing Han, Y. Qian, Michael Zeng","doi":"10.1109/SLT54892.2023.10022470","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10022470","url":null,"abstract":"In real application scenarios, it is often challenging to obtain a large amount of labeled data for speaker representation learning due to speaker privacy concerns. Self-supervised learning with no labels has become a more and more promising way to solve it. Compared with contrastive learning, self-distilled approaches use only positive samples in the loss function and thus are more attractive. In this paper, we present a comprehensive study on self-distilled self-supervised speaker representation learning, especially on critical data augmentation. Our proposed strategy of audio perturbation augmentation has pushed the performance of the speaker representation to a new limit. The experimental results show that our model can achieve a new SoTA on Voxceleb 1 speaker verification evaluation benchmark (i.e., equal error rate (EER) 2.505%, 2.473%, and 4.791 % for trial Vox1-O, Vox1-E and Vox1-H, respectively), discarding any speaker labels in the training phase.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125031393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis 基于情态特征的大规模预训练编码器在多情态情感分析中的应用
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-28 DOI: 10.1109/SLT54892.2023.10022548
Atsushi Ando, Ryo Masumura, Akihiko Takashima, Satoshi Suzuki, Naoki Makishima, Keita Suzuki, Takafumi Moriya, Takanori Ashihara, Hiroshi Sato
{"title":"On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis","authors":"Atsushi Ando, Ryo Masumura, Akihiko Takashima, Satoshi Suzuki, Naoki Makishima, Keita Suzuki, Takafumi Moriya, Takanori Ashihara, Hiroshi Sato","doi":"10.1109/SLT54892.2023.10022548","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10022548","url":null,"abstract":"This paper investigates the effectiveness and implementation of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis (MSA). Although the effectiveness of pre-trained encoders in various fields has been reported, conventional MSA methods employ them for only linguistic modality, and their application has not been investigated. This paper compares the features yielded by large-scale pre-trained encoders with conventional heuristic features. One each of the largest pre-trained encoders publicly available for each modality are used; CLIP-ViT, WavLM, and BERT for visual, acoustic, and linguistic modalities, respectively. Experiments on two datasets reveal that methods with domain-specific pre-trained encoders attain better performance than those with conventional features in both unimodal and multimodal scenarios. We also find it better to use the outputs of the intermediate layers of the encoders than those of the output layer. The codes are available at https://github.com/ando-hub/MSA_Pretrain.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"71 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131435920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Monotonic Segmental Attention for Automatic Speech Recognition 语音自动识别中的单调分段注意
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-26 DOI: 10.1109/SLT54892.2023.10022818
Albert Zeyer, Robin Schmitt, Wei Zhou, R. Schluter, H. Ney
{"title":"Monotonic Segmental Attention for Automatic Speech Recognition","authors":"Albert Zeyer, Robin Schmitt, Wei Zhou, R. Schluter, H. Ney","doi":"10.1109/SLT54892.2023.10022818","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10022818","url":null,"abstract":"We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming. We directly compare global-attention and different segmental-attention modeling variants. We develop and compare two separate time-synchronous decoders, one specifically taking the segmental nature into account, yielding further improvements. Using time-synchronous decoding for segmental models is novel and a step towards streaming applications. Our experiments show the importance of a length model to predict the segment boundaries. The final best segmental-attention model using segmental decoding performs better than global-attention, in contrast to other monotonic attention approaches in the literature. Further, we observe that the segmental model generalizes much better to long sequences of up to several minutes.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129435318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Four-in-One: a Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition 四合一:用于自动语音识别的反文本规范化、标点、大写和不流畅性的联合方法
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-26 DOI: 10.1109/SLT54892.2023.10023257
S.S. Tan, Piyush Behre, Nick Kibre, Issac Alphonso, Shuangyu Chang
{"title":"Four-in-One: a Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition","authors":"S.S. Tan, Piyush Behre, Nick Kibre, Issac Alphonso, Shuangyu Chang","doi":"10.1109/SLT54892.2023.10023257","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10023257","url":null,"abstract":"Features such as punctuation, capitalization, and formatting of entities are important for readability, understanding, and natural language processing tasks. However, Automatic Speech Recognition (ASR) systems produce spoken-form text devoid of formatting, and tagging approaches to formatting address just one or two features at a time. In this paper, we unify spoken-to-written text conversion via a two-stage process: First, we use a single transformer tagging model to jointly produce token-level tags for inverse text normalization (ITN), punctuation, capitalization, and disfluencies. Then, we apply the tags to generate written-form text and use weighted finite state transducer (WFST) grammars to format tagged ITN entity spans. Despite joining four models into one, our unified tagging approach matches or outperforms task-specific models across all four tasks on benchmark test sets across several domains.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"74 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131758473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using ß-VAE 基于ß-VAE的单次跨语言语音转换解纠缠语音表示学习
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-25 DOI: 10.1109/SLT54892.2023.10022787
Hui Lu, Disong Wang, Xixin Wu, Zhiyong Wu, Xunying Liu, Helen M. Meng
{"title":"Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using ß-VAE","authors":"Hui Lu, Disong Wang, Xixin Wu, Zhiyong Wu, Xunying Liu, Helen M. Meng","doi":"10.1109/SLT54892.2023.10022787","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10022787","url":null,"abstract":"We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the effectiveness of the disentanglement. Inspired by ß- VAE, we introduce a learning objective that balances between the information captured by the content and speaker representations. In addition, the inductive biases from the architectural design and the training dataset further encourage the desired disentanglement. Both objective and subjective evaluations show the effectiveness of the proposed method in speech disentanglement and in one-shot cross-lingual voice conversion.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129107689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Weak-Supervised Dysarthria-Invariant Features for Spoken Language Understanding Using an Fhvae and Adversarial Training 弱监督构音障碍不变特征在口语理解中的应用
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-24 DOI: 10.1109/SLT54892.2023.10023085
Jinzi Qi, H. V. hamme
{"title":"Weak-Supervised Dysarthria-Invariant Features for Spoken Language Understanding Using an Fhvae and Adversarial Training","authors":"Jinzi Qi, H. V. hamme","doi":"10.1109/SLT54892.2023.10023085","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10023085","url":null,"abstract":"The scarcity of training data and the large speaker variation in dysarthric speech lead to poor accuracy and poor speaker generalization of spoken language understanding systems for dysarthric speech. Through work on the speech features, we focus on improving the model generalization ability with limited dysarthric data. Factorized Hierarchical Variational Auto-Encoders (FHVAE) trained unsupervisedly have shown their advantage in disentangling content and speaker representations. Earlier work showed that the dysarthria shows in both feature vectors. Here, we add adversarial training to bridge the gap between the control and dysarthric speech data domains. We extract dysarthric and speaker invariant features using weak supervision. The extracted features are evaluated on a Spoken Language Understanding task and yield a higher accuracy on unseen speakers with more severe dysarthria compared to features from the basic FHVAE model or plain filterbanks.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114303972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Proficiency Assessment of L2 Spoken English Using Wav2Vec 2.0 使用Wav2Vec 2.0进行第二语言口语水平评估
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-24 DOI: 10.1109/SLT54892.2023.10023019
Stefano Bannò, M. Matassoni
{"title":"Proficiency Assessment of L2 Spoken English Using Wav2Vec 2.0","authors":"Stefano Bannò, M. Matassoni","doi":"10.1109/SLT54892.2023.10023019","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10023019","url":null,"abstract":"The increasing demand for learning English as a second language has led to a growing interest in methods for automatically assessing spoken language proficiency. Most approaches use hand-crafted features, but their efficacy relies on their particular underlying assumptions and they risk discarding potentially salient information about proficiency. Other approaches rely on transcriptions produced by ASR systems which may not provide a faithful rendition of a learner's utterance in specific scenarios (e.g., non-native children's spontaneous speech). Furthermore, transcriptions do not yield any information about relevant aspects such as intonation, rhythm or prosody. In this paper, we investigate the use of wav2vec 2.0 for assessing overall and individual aspects of proficiency on two small datasets, one of which is publicly available. We find that this approach significantly outperforms the BERT-based baseline system trained on ASR and manual transcriptions used for comparison.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129419940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition 自动语音识别的引导对比自监督预训练
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-22 DOI: 10.1109/SLT54892.2023.10022676
Aparna Khare, Minhua Wu, Saurabhchand Bhati, J. Droppo, R. Maas
{"title":"Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition","authors":"Aparna Khare, Minhua Wu, Saurabhchand Bhati, J. Droppo, R. Maas","doi":"10.1109/SLT54892.2023.10022676","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10022676","url":null,"abstract":"Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given model. It can be used to effectively initialize the encoder of an Automatic Speech Recognition (ASR) model. We present a novel modification of CPC called Guided Contrastive Predictive Coding (GCPC). Our proposed method maximizes the mutual information between representations from a prior-knowledge model and the output of the model being pre-trained, allowing prior knowledge injection during pre-training. We validate our method on 3 ASR tasks: German, French and English. Our method outperforms CPC pre-training on all three datasets, reducing the Word Error Rate (WER) by 4.44%, 6.55% and 15.43% relative on the German, French and English (Librispeech) tasks respectively, compared to training from scratch, while CPC pre-training only brings 2.96%, 1.01% and 14.39% relative WER reduction respectively.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114503850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis 结合对比和非对比损失对语音分析中预训练模型进行微调
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-21 DOI: 10.1109/SLT54892.2023.10022897
Florian Lux, Ching-Yi Chen, Ngoc Thang Vu
{"title":"Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis","authors":"Florian Lux, Ching-Yi Chen, Ngoc Thang Vu","doi":"10.1109/SLT54892.2023.10022897","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10022897","url":null,"abstract":"Embedding paralinguistic properties is a challenging task as there are only a few hours of training data available for domains such as emotional speech. One solution to this problem is to pretrain a general self-supervised speech representation model on large amounts of unlabeled speech. This pretrained model is then finetuned to a specific task. Paralinguistic properties however have notoriously high class variance, making the finetuning ineffective. In this work, we propose a two step approach to this. First we improve the embedding space, then we train an adapter to bridge the gap from the embedding space to a classification task. In order to improve the class invariance we use a combination of contrastive and non-contrastive losses to explicitly optimize for class invariant, yet discriminative features. Our approach consistently outperforms baselines that are finetuned end-to-end on multiple tasks and surpasses a benchmark on state-of-the-art emotion classification.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122441946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Improved Normalizing Flow-Based Speech Enhancement Using an all-Pole Gammatone Filterbank for Conditional Input Representation 基于条件输入表示的全极伽玛酮滤波器组的改进归一化流语音增强
2022 IEEE Spoken Language Technology Workshop (SLT) Pub Date : 2022-10-21 DOI: 10.1109/SLT54892.2023.10022898
Martin Strauss, Matteo Torcoli, B. Edler
{"title":"Improved Normalizing Flow-Based Speech Enhancement Using an all-Pole Gammatone Filterbank for Conditional Input Representation","authors":"Martin Strauss, Matteo Torcoli, B. Edler","doi":"10.1109/SLT54892.2023.10022898","DOIUrl":"https://doi.org/10.1109/SLT54892.2023.10022898","url":null,"abstract":"Deep generative models for Speech Enhancement (SE) received increasing attention in recent years. The most prominent example are Generative Adversarial Networks (GANs), while normalizing flows (NF) received less attention despite their potential. Building on previous work, architectural modifications are proposed, along with an investigation of different conditional input representations. Despite being a common choice in related works, Mel-spectrograms demonstrate to be inadequate for the given scenario. Alternatively, a novel All-Pole Gammatone filterbank (APG) with high temporal resolution is proposed. Although computational evaluation metric results would suggest that state-of-the-art GAN-based methods perform best, a perceptual evaluation via a listening test indicates that the presented NF approach (based on time domain and APG) performs best, especially at lower SNRs. On average, APG outputs are rated as having good quality, which is unmatched by the other methods, including GAN.","PeriodicalId":352002,"journal":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132555896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信