Computer Speech and Language最新文献

{"title":"Enhancing Turkish Coreference Resolution: Insights from deep learning, dropped pronouns, and multilingual transfer learning","authors":"Tuğba Pamay Arslan,&nbsp;Gülşen Eryiğit","doi":"10.1016/j.csl.2024.101681","DOIUrl":"https://doi.org/10.1016/j.csl.2024.101681","url":null,"abstract":"<div><p>Coreference resolution (CR), which is the identification of in-text mentions that refer to the same entity, is a crucial step in natural language understanding. While CR in English has been studied for quite a long time, studies for pro-dropped and morphologically rich languages is an active research area which has yet to reach sufficient maturity. Turkish, a morphologically highly-rich language, poses interesting challenges for natural language processing tasks, including CR, due to its agglutinative nature and consequent pronoun-dropping phenomenon. This article explores the use of different neural CR architectures (i.e., mention-pair, mention-ranking, and end-to-end) on Turkish, a morphologically highly-rich language, by formulating multiple research questions around the impacts of dropped pronouns, data quality, and interlingual transfer. The preparations made to explore these research questions and the findings obtained as a result of our explorations revealed the first Turkish CR dataset that includes dropped pronoun annotations (of size 4K entities/22K mentions), new state-of-the-art results on Turkish CR, the first neural end-to-end Turkish CR results (70.4% F-score), the first multilingual end-to-end CR results including Turkish (yielding 1.0 percentage points improvement on Turkish) and the demonstration of the positive impact of dropped pronouns on CR of pro-dropped and morphologically rich languages, for the first time in the literature. Our research has brought Turkish end-to-end CR performances (72.0% F-score) to similar levels with other languages, surpassing the baseline scores by 32.1 percentage points.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101681"},"PeriodicalIF":3.1,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000640/pdfft?md5=75cd60c63807520ee823be3bbb1025ae&pid=1-s2.0-S0885230824000640-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141444378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quality achhi hai (is good), satisfied! Towards aspect based sentiment analysis in code-mixed language","authors":"Mamta ,&nbsp;Asif Ekbal","doi":"10.1016/j.csl.2024.101668","DOIUrl":"10.1016/j.csl.2024.101668","url":null,"abstract":"<div><p>Social media, e-commerce, and other online platforms have witnessed tremendous growth in multilingual users. This requires addressing the code-mixing phenomenon, i.e. mixing of more than one language for providing a rich native user experience. User reviews and comments may benefit service providers in terms of customer management. Aspect based Sentiment Analysis (ABSA) provides a fine-grained analysis of these reviews by identifying the aspects mentioned and classifies the polarities (i.e., positive, negative, neutral, and conflict). The research in this direction has mainly focused on resource-rich monolingual languages like English, which does not suffice for analyzing multilingual code-mixed reviews. In this paper, we introduce a new task to facilitate the research on code-mixed ABSA. We offer a benchmark setup by creating a code-mixed Hinglish (i.e., mixing of Hindi and English) dataset for ABSA, which is annotated with aspect terms and their sentiment values. To demonstrate the effective usage of the dataset, we develop several deep learning based models for aspect term extraction and sentiment analysis, and establish them as the baselines for further research in this direction. <span>¹</span></p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101668"},"PeriodicalIF":4.3,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000512/pdfft?md5=d4cf7f510d6f46e21b19e99b8421ebc3&pid=1-s2.0-S0885230824000512-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141399023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TadaStride: Using time adaptive strides in audio data for effective downsampling","authors":"Yoonhyung Lee ,&nbsp;Kyomin Jung","doi":"10.1016/j.csl.2024.101678","DOIUrl":"10.1016/j.csl.2024.101678","url":null,"abstract":"<div><p>In this paper, we introduce a new downsampling method for audio data called TadaStride, which can adaptively adjust the downsampling ratios across an audio data instance. Unlike previous methods using a fixed downsampling ratio, TadaStride can preserve more information from task-relevant parts of a data instance by using smaller strides for those parts and larger strides for less relevant parts. Additionally, we also introduce TadaStride-F, which is developed as a more efficient version of TadaStride while maintaining minimal performance loss. In experiments, we evaluate our TadaStride, primarily focusing on a range of audio processing tasks. Firstly, in audio classification experiments, TadaStride and TadaStride-F outperform other widely used standard downsampling methods, even with comparable memory and time usage. Furthermore, through various analyses, we provide an understanding of how TadaStride learns effective adaptive strides and how it leads to improved performance. In addition, through additional experiments on automatic speech recognition and discrete speech representation learning, we demonstrate that TadaStride and TadaStride-F consistently outperform other downsampling methods and examine how the adaptive strides are learned in these tasks.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101678"},"PeriodicalIF":3.1,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000615/pdfft?md5=5861e2f1cdebf31ffd61d0cba92056f3&pid=1-s2.0-S0885230824000615-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141412883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic study of DNN based speech enhancement in reverberant and reverberant-noisy environments","authors":"Heming Wang ,&nbsp;Ashutosh Pandey ,&nbsp;DeLiang Wang","doi":"10.1016/j.csl.2024.101677","DOIUrl":"https://doi.org/10.1016/j.csl.2024.101677","url":null,"abstract":"<div><p>Deep learning has led to dramatic performance improvements for the task of speech enhancement, where deep neural networks (DNNs) are trained to recover clean speech from noisy and reverberant mixtures. Most of the existing DNN-based algorithms operate in the frequency domain, as time-domain approaches are believed to be less effective for speech dereverberation. In this study, we employ two DNNs: ARN (attentive recurrent network) and DC-CRN (densely-connected convolutional recurrent network), and systematically investigate the effects of different components on enhancement performance, such as window sizes, loss functions, and feature representations. We conduct evaluation experiments in two main conditions: reverberant-only and reverberant-noisy. Our findings suggest that incorporating larger window sizes is helpful for dereverberation, and adding transform operations (either convolutional or linear) to encode and decode waveform features improves the sparsity of the learned representations, and boosts the performance of time-domain models. Experimental results demonstrate that ARN and DC-CRN with proposed techniques achieve superior performance compared with other strong enhancement baselines.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101677"},"PeriodicalIF":4.3,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000603/pdfft?md5=6f57ae0077f304562bdf74000559d71d&pid=1-s2.0-S0885230824000603-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141325435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MPSA-DenseNet: A novel deep learning model for English accent classification","authors":"Tianyu Song ,&nbsp;Linh Thi Hoai Nguyen ,&nbsp;Ton Viet Ta","doi":"10.1016/j.csl.2024.101676","DOIUrl":"https://doi.org/10.1016/j.csl.2024.101676","url":null,"abstract":"<div><p>This paper presents three innovative deep learning models for English accent classification: Multi-task Pyramid Split Attention- Densely Convolutional Networks (MPSA-DenseNet), Pyramid Split Attention- Densely Convolutional Networks (PSA-DenseNet), and Multi-task- Densely Convolutional Networks (Multi-DenseNet), that combine multi-task learning and/or the PSA module attention mechanism with DenseNet. We applied these models to data collected from five dialects of English across native English-speaking regions (England, the United States) and nonnative English-speaking regions (Hong Kong, Germany, India). Our experimental results show a significant improvement in classification accuracy, particularly with MPSA-DenseNet, which outperforms all other models, including Densely Convolutional Networks (DenseNet) and Efficient Pyramid Squeeze Attention (EPSA) models previously used for accent identification. Our findings indicate that MPSA-DenseNet is a highly promising model for accurately identifying English accents.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101676"},"PeriodicalIF":4.3,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000597/pdfft?md5=45eac4ef8fe33cc3af54ca5ce1756899&pid=1-s2.0-S0885230824000597-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141264076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel and secured email classification using deep neural network with bidirectional long short-term memory","authors":"A. Poobalan ,&nbsp;K. Ganapriya ,&nbsp;K. Kalaivani ,&nbsp;K. Parthiban","doi":"10.1016/j.csl.2024.101667","DOIUrl":"https://doi.org/10.1016/j.csl.2024.101667","url":null,"abstract":"<div><p>Email data has some characteristics that are different from other social media data, such as a large range of answers, formal language, notable length variations, high degrees of anomalies, and indirect relationships. The main goal in this research is to develop a robust and computationally efficient classifier that can distinguish between spam and regular email content. The benchmark Enron dataset, which is accessible to the public, was used for the tests. The six distinct Enron data sets we acquired were combined to generate the final seven Enron data sets. The dataset undergoes early preprocessing to remove superfluous sentences. The proposed model Bidirectional Long Short-Term Memory (BiLSTM) apply spam labels and to examine email documents for spam. On seven Enron datasets, DNN-BiLSTM performs better than other classifiers in the performance comparison in terms of accuracy. DNN-BiLSTM and convolutional neural networks demonstrated that they can classify spam with 96.39 % and 98.69 % accuracy, respectively, in comparison to other machine learning classifiers. The risks associated with cloud data management and potential security flaws are also covered in the paper. This research presents hybrid encryption as a means of protecting cloud data while preserving privacy by using the hybrid AES-Rabit encryption algorithm which is based on symmetric session key exchange.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101667"},"PeriodicalIF":4.3,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000500/pdfft?md5=93a3ab04f63a63c4343031dc3b1f9eca&pid=1-s2.0-S0885230824000500-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141250220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Speech emotion recognition in real static and dynamic human-robot interaction scenarios","authors":"Nicolás Grágeda ,&nbsp;Carlos Busso ,&nbsp;Eduardo Alvarado ,&nbsp;Ricardo García ,&nbsp;Rodrigo Mahu ,&nbsp;Fernando Huenupan ,&nbsp;Néstor Becerra Yoma","doi":"10.1016/j.csl.2024.101666","DOIUrl":"10.1016/j.csl.2024.101666","url":null,"abstract":"<div><p>The use of speech-based solutions is an appealing alternative to communicate in human-robot interaction (HRI). An important challenge in this area is processing distant speech which is often noisy, and affected by reverberation and time-varying acoustic channels. It is important to investigate effective speech solutions, especially in dynamic environments where the robots and the users move, changing the distance and orientation between a speaker and the microphone. This paper addresses this problem in the context of speech emotion recognition (SER), which is an important task to understand the intention of the message and the underlying mental state of the user. We propose a novel setup with a PR2 robot that moves as target speech and ambient noise are simultaneously recorded. Our study not only analyzes the detrimental effect of distance speech in this dynamic robot-user setting for speech emotion recognition but also provides solutions to attenuate its effect. We evaluate the use of two beamforming schemes to spatially filter the speech signal using either delay-and-sum (D&amp;S) or minimum variance distortionless response (MVDR). We consider the original training speech recorded in controlled situations, and simulated conditions where the training utterances are processed to simulate the target acoustic environment. We consider the case where the robot is moving (dynamic case) and not moving (static case). For speech emotion recognition, we explore two state-of-the-art classifiers using hand-crafted features implemented with the ladder network strategy and learned features implemented with the wav2vec 2.0 feature representation. MVDR led to a signal-to-noise ratio higher than the basic D&amp;S method. However, both approaches provided very similar average concordance correlation coefficient (CCC) improvements equal to 116 % with the HRI subsets using the ladder network trained with the original MSP-Podcast training utterances. For the wav2vec 2.0-based model, only D&amp;S led to improvements. Surprisingly, the static and dynamic HRI testing subsets resulted in a similar average concordance correlation coefficient. Finally, simulating the acoustic environment in the training dataset provided the highest average concordance correlation coefficient scores with the HRI subsets that are just 29 % and 22 % lower than those obtained with the original training/testing utterances, with ladder network and wav2vec 2.0, respectively.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101666"},"PeriodicalIF":4.3,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000494/pdfft?md5=10d8a0faec641adaf8be74271eaf5174&pid=1-s2.0-S0885230824000494-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141134350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An exploratory characterization of speech- and fine-motor coordination in verbal children with Autism spectrum disorder","authors":"Tanya Talkar ,&nbsp;James R. Williamson ,&nbsp;Sophia Yuditskaya ,&nbsp;Daniel J. Hannon ,&nbsp;Hrishikesh M. Rao ,&nbsp;Lisa Nowinski ,&nbsp;Hannah Saro ,&nbsp;Maria Mody ,&nbsp;Christopher J. McDougle ,&nbsp;Thomas F. Quatieri","doi":"10.1016/j.csl.2024.101665","DOIUrl":"10.1016/j.csl.2024.101665","url":null,"abstract":"<div><p>Autism spectrum disorder (ASD) is a neurodevelopmental disorder often associated with difficulties in speech production and fine-motor tasks. Thus, there is a need to develop objective measures to assess and understand speech production and other fine-motor challenges in individuals with ASD. In addition, recent research suggests that difficulties with speech production and fine-motor tasks may contribute to language difficulties in ASD. In this paper, we explore the utility of an off-body recording platform, from which we administer a speech- and fine-motor protocol to verbal children with ASD and neurotypical controls. We utilize a correlation-based analysis technique to develop proxy measures of motor coordination from signals derived from recordings of speech- and fine-motor behaviors. Eigenvalues of the resulting correlation matrix are inputs to Gaussian Mixture Models to discriminate between highly-verbal children with ASD and neurotypical controls. These eigenvalues also characterize the complexity (underlying dimensionality) of representative signals of speech- and fine-motor movement dynamics, and form the feature basis to estimate scores on an expressive vocabulary measure. Based on a pilot dataset (15 ASD and 15 controls), features derived from an oral story reading task are used in discriminating between the two groups with AUCs &gt; 0.80, and highlight lower complexity of coordination in children with ASD. Features derived from handwriting and maze tracing tasks led to AUCs of 0.86 and 0.91, however features derived from ocular tasks did not aid in discrimination between the ASD and neurotypical groups. In addition, features derived from free speech and sustained vowel tasks are strongly correlated with expressive vocabulary scores. These results indicate the promise of a correlation-based analysis in elucidating motor differences between individuals with ASD and neurotypical controls.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101665"},"PeriodicalIF":4.3,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000482/pdfft?md5=6554015220341426a1f33615cd53fd75&pid=1-s2.0-S0885230824000482-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141139333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A potential relation trigger method for entity-relation quintuple extraction in text with excessive entities","authors":"Xiaojun Xia ,&nbsp;Yujiang Liu ,&nbsp;Lijun Fu","doi":"10.1016/j.csl.2024.101650","DOIUrl":"10.1016/j.csl.2024.101650","url":null,"abstract":"<div><p>In the task of joint entity and relation extraction, the relationship between two entities is determined by some specific words in their source text. These words are viewed as potential triggers which are the evidence to explain the relationship but not marked clearly. However, the current models cannot make good use of the potential words to optimize components of entities and relations, but can only give separate results. These models aim to identify the type of relation between two entities mentioned in the source text by encoding the text and entities. Although some models can generate the weights for every single word by improving the attention mechanism, the weights will be influenced by the irrelevant words essentially, which is not needed in enhancing the influence of the triggers. We propose a joint entity-relation quintuple extraction framework based on the Potential Relation Trigger (PRT) method to get the highest probability of a word as the prompt in every time step and join the words together as relation hints. In specific, we leverage polarization mechanism in possibility calculation to avoid nondifferentiable points of the functions in our method when choosing. We find that their representation will improve the performance of the relation part with the exact range of the entities. Extensive experiments results demonstrate that the effectiveness of our proposed model achieves state-of-the-art performance on four RE benchmark datasets.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"89 ","pages":"Article 101650"},"PeriodicalIF":4.3,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0885230824000330/pdfft?md5=394e6ed4d34c985c0397218c2f0043ed&pid=1-s2.0-S0885230824000330-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141047279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Room impulse response reshaping-based expectation–maximization in an underdetermined reverberant environment","authors":"Yuan Xie ,&nbsp;Tao Zou ,&nbsp;Junjie Yang ,&nbsp;Weijun Sun ,&nbsp;Shengli Xie","doi":"10.1016/j.csl.2024.101664","DOIUrl":"10.1016/j.csl.2024.101664","url":null,"abstract":"<div><p>Source separation in an underdetermined reverberation environment is a very challenging issue. The classical method is based on the expectation–maximization algorithm. However, it is limited to high reverberation environments, resulting in bad or even invalid separation performance. To eliminate this restriction, a room impulse response reshaping-based expectation–maximization method is designed to solve the problem of source separation in an underdetermined reverberant environment. Firstly, a room impulse response reshaping technology is designed to eliminate the influence of audible echo on the reverberant environment, improving the quality of the received signals. Then, a new mathematical model of time-frequency mixing signals is established to reduce the approximation error of model transformation caused by high reverberation. Furthermore, an improved expectation–maximization method is proposed for real-time update learning rules of model parameters, and then the sources are separated using the estimators provided by the improved expectation–maximization method. Experimental results based on source separation of speech and music mixtures demonstrate that the proposed algorithm achieves better separation performance while maintaining much better robustness than popular expectation–maximization methods.</p></div>","PeriodicalId":50638,"journal":{"name":"Computer Speech and Language","volume":"88 ","pages":"Article 101664"},"PeriodicalIF":4.3,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141047534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}