Audio News Research Articles

Research on the Integrated Development Strategy of Future News Industry in the Smart Speaker Scene

Research on the Integrated Development Strategy of Future News Industry in the Smart Speaker Scene

Optimization of the visual communication path of data news in the context of the Internet

Abstract Visual news belongs to a kind of data news, which uses emerging technology to bring users a new reading experience and improve the news dissemination effect. In this paper, we utilize the self-attention mechanism and BiLSTM model to extract the content of data news documents and select and classify the audio features of data news by the AdaBoost algorithm. ResNet50 is used as the backbone network, combined with multiple residual unit modules for news multi-scale image feature extraction, and the text, audio and image features of the data news are fused by constructing a multimodal feature adaptive fusion model to further optimize the visual display of the data news. This paper verifies the model’s effectiveness for the data news visualization technique through multiple perspectives, including training loss curve, performance comparison, and ablation experiment. The results show that the loss value of the model based on the Self-Attention-BiLSTM model for news text feature extraction is 0.211 after 150 iterations. The AdaBoost-based news audio feature classification method has an average classification accuracy of 97.56% for the positive diagonal when the noise is raised from 0dB to 30 dB. By adding the residual unit module to the ResNet50 backbone network, the accuracy of the multi-scale image feature extraction model has been improved by 2.77% compared to the single backbone network. The information age requires the full integration of technology and news and combining the corresponding Internet platform for the visual display of data news in order to promote the expansion of the visual communication path of data news.

Democratic listening: News podcasts, trust and political participation in Australia

This article illustrates how news podcasts are playing a productive role in animating democracy in Australia. Drawing on findings from an exploratory online survey, it highlights how audiences view news podcasts as an important enabler of their participation in democratic life, and that news podcast listeners are likely to engage in both latent and manifest forms of political action. It also indicates that news podcast listeners are discerning media consumers, and that news podcasts are valued for reasons of both convenience and content. With limited prior research into the relationship between podcast listening and civic engagement, this article provides evidence for how this relatively new podcast genre is prized for its ability to enhance democratic life in Australia. It also problematizes the notion of trust in audio news, signalling a key avenue for further research examining the interplay between traditional markers of journalistic authority and more emotional styles of podcast journalism storytelling.

Los podcasts informativos diarios en España: evolución de la oferta y aportaciones narrativas del formato

The success of The Daily’s news podcast a relatively new audio format employed by a traditional newspaper, with a different narrative and aesthetic approach next to modern-day radio news has inspired similar podcasts by other major news outlets from around the world, both print and digital. Our work describes the appearance and development of various news podcasts in Spain and proposes a comparative analysis of the three most competitive podcasts: El mundo al día, by the newspaper El Mundo; Un tema al día, by elDiario; and Hoy en El País, by El País. Through a quantitative and qualitative study of 28 narrative, expressive, and strategic variables, the study systematizes the defining traits of a format that has renewed audio news stories and turned audio into a new and increasingly efficient communication channel for news outlets. The results reveal that this format can really help explain  and not just talk about current events. It is closely tied to the figure of the narrator or newscaster, and it allows listeners to understand and value the efforts of journalists. It thus becomes a valuable documentary repository of digital audio, easily retrieved and reused.  

From Black Lives Matter to COVID-19: Daily news podcasts and the reinvention of audio reporting

Globally daily news podcasts have exponentially grown in popularity. To build on the increased interest in this podcast format, this study examines three distinct programmes in this genre. The focus of our research specifically highlights the significant news events during the summer of 2020: the killing of George Floyd, and subsequent Black Lives Matter protests, and the COVID-19 pandemic. Using a set of genre conventions adapted and expanded from previous podcast and radio news scholarship, this research analyses the impact podcasting has on daily audio news production. Our findings indicate the podcast host’s empathy and intimacy, coalesced into powerful, immersive deep dive discussions. Those kinds of conversations have strongly influenced and transformed daily news production, while still maintaining journalistic ethics and aesthetics.

Audio Storytelling Innovation in a Digital Age: The Case of Daily News Podcasts in Spain

On the 1st of February 2017, The New York Times published the first episode of ‘The Daily’, a news podcast hosted by Michael Barbaro that, five years later, has become the most popular in the world with four million listeners each day and more than 3000 million accumulated downloads. The unprecedented success of this audio format, that has emerged in a traditional newspaper, has helped to revamp radio news and has spread in various versions all over the world. This investigation analyses daily podcasts in Spain and, by means of a quantitative and qualitative study, identifies their main themes, narrative structures, and expressive contributions based on four illustrative experiences in this market: ‘Quién dice qué‘, ‘AM’, ‘El Mundo al día’, and ‘Un tema al día’. The results reveal the consolidation of two clearly defined models: a more conventional one based on radio bulletins and news reports; and another, more innovative model that replicates the anglophone formula that opts for depth, dissemination, and a conversational tone to redefine the canons of the audio news narrative and take advantage of the potential of audio as a new distribution channel for newspapers in the digital eco-system.

Supporting listening comprehension by social network-based interaction in mobile assisted language learning

Listening comprehension is challenging for students because it is more than just the direct extraction of meaning from sound. The literature reflects the need to develop relevant strategies. Teachers typically try to help students structure their learning into three phases: before (pre-), during, and after (post-) listening, emphasizing different cognitive and metacognitive processes. In this paper, the role of MALL (Mobile Assisted Language Learning) is proposed as a way to support this learning process and specifically to scaffold its third phase. A study was carried out with an app that the authors have developed for listening to audio news recordings. There are two versions of this app; the first is a standalone program which the students use on an individual basis. The second links to Facebook to enable students to summarize, share and discuss what they have listened to, thereby refining and consolidating their comprehension. A research question in this study addressed the role of a social network in a MALL app in terms of motivation and learning habits. The results of the study provide pedagogical insights into the answer and the value of including social network-based interaction in a MALL app for the development of listening comprehension.

A Case Study of the Ideological and Political Education of College English Translation Course Driven by Words

It takes the new words and phrases from iEnglish (an Integrated Course I) as the basic translation materials, and it takes the articles from “xuexi.cn (学习强国)” platform “China Daily Audio News” column as the elements of ideological and political education. The articles from China Daily Audio News include 10 pieces. The articles’ dates are from November 5, 2020 to December 4, 2020. Through searching and underlining the new words and phrases in the articles, it contains three layers, that is, the translation of short sentences, the translation of long difficult sentences, and the translation of excerpts of passages to carry on the analysis, to study the use of words with ideological and political education. Do put this into use, and thus output in line with the socialist values of talents.

El rol de las redes sociales en la comprensión oral de segundas lenguas con soporte móvil

La comprensión oral es una competencia importante para quien estudia una segunda lengua, pero requiere una práctica y una orientación significativas. Existe un volumen considerable de literatura sobre los factores que intervienen, por un lado, en el desarrollo de la competencia oral, que pueden clasificarse como perceptuales, cognitivos o metacognitivos y, por otro, en las estrategias de la enseñanza y el aprendizaje que apoyan dicho proceso. Los autores de este artículo desarrollaron una app de aprendizaje asistido de lenguas (MALL según el acrónimo inglés), denominada ANT (Audio News Trainer), para apoyar a los estudiantes en dicho aprendizaje, ofreciéndoles grabaciones de audio con noticias de actualidad y actividades de aprendizaje relacionadas con ellas. Hay dos versiones de la aplicación, una es para el uso individual y otra está vinculada a Facebook para potenciar los aspectos psicopedagógicos relevantes en el desarrollo de la comprensión oral. En este artículo se exploran dos preguntas de investigación acerca del uso de dicha red social para motivar a los estudiantes y para ayudarles a que se autorregulen mejor respectivamente, utilizando cuestionarios y datos experimentales recopilados del uso de ANT. Los resultados obtenidos de estos análisis muestran que la interacción guiada entre estudiantes de una segunda lengua en la red social Facebook causa un impacto significativo en la motivación y en la autorregulación que acompañan la evolución de la comprensión oral.

Classification of Broadcast News Audio Data Employing Binary Decision Architecture

A novel binary decision architecture (BDA) for broadcast news audio classification task is presented in this paper. The idea of developing such architecture came from the fact that the appropriate combination of multiple binary classifiers for two-class discrimination problem can reduce a miss-classification error without rapid increase in computational complexity. The core element of classification architecture is represented by a binary decision (BD) algorithm that performs discrimination between each pair of acoustic classes, utilizing two types of decision functions. The first one is represented by a simple rule-based approach in which the final decision is made according to the value of selected discrimination parameter. The main advantage of this solution is relatively low processing time needed for classification of all acoustic classes. The cost for that is low classification accuracy. The second one employs support vector machine (SVM) classifier. In this case, the overall classification accuracy is conditioned by finding the optimal parameters for decision function resulting in higher computational complexity and better classification performance. The final form of proposed BDA is created by combining four BD discriminators supplemented by decision table. The effectiveness of proposed BDA, utilizing rule-based approach and the SVM classifier, is compared with two most popular strategies for multiclass classification, namely the binary decision trees (BDT) and the One-Against-One SVM (OAOSVM). Experimental results show that the proposed classification architecture can decrease the overall classification error in comparison with the BDT architecture. On the contrary, an optimization technique for selecting the optimal set of training data is needed in order to overcome the OAOSVM.

METACOGNITION AS SCAFFOLDING FOR THE DEVELOPMENT OF LISTENING COMPREHENSION IN A SOCIAL MALL APP

This article focuses on the role that metacognition can effectively play in the development of second language listening comprehension, and specifically, how a mobile app can be specified for this end. A social mobile assisted listening app, ANT (Audio News Trainer), is presented as a prototype for exploring the way in which students can be helped to use metacognition to improve relevant linguistic communicative competences. A study has been undertaken with students using ANT to explore the intricate nature of the listening comprehension development process and the main metacognitive strategies that can be successfully applied. Special attention is paid to the implicitly and explicitly applied metacognitive strategies within the app, and related social network, where follow-on activities were undertaken, the strategies in question being: focus (a conscious effort on the gradual development of individual skills), engagement (interest is enhanced when a learning activity is enjoyable/successful), interaction (since collective activities seem to enhance emotional and social involvement), reflection (upon what works and does not work for each individual), self-regulation (through data about the students’ own progress and achievements), and attitude (here a further distinction is made between satisfaction, self-confidence and encouragement). The stages of engagement of a student with the app are explored in relation to the metacognitive strategy used and how they can contribute to the overall success of the learning experience. A final reflection is made about how metacognitive strategies offer an effective way to compensate for the lack of teacher presence, support and guidance on a medium/long term basis. However, although the study of the initial use of this social listening training app shows the potential for incorporating ‘knowing about knowing’ into mobile technology, it is suggested that future research is required to provide further finer-grained insights into this process.

May the Sorts Be with You

More and more investors are tracking and analyzing news flows and text sentiments in large, unstructured datasets and mining data in a split second for investment-relevant information. Often, the goal is to incorporate findings into trading strategies and algorithms, to back-test investment theses, or to improve risk-monitoring activities. Finding information of interest in large, textual databases is becoming easier as semantic analytic technologies mature. Tools already abound to help companies monitor the sentiment toward their brands by evaluating “big data” repositories, such as customer comments. Text and news analytics for investing is a newer niche application, and many are now experimenting with investment use cases. As they do, the need to quantify and incorporate unstructured data into investing equations continues to grow, along with the volume of textual data: About 2.5 billion gigabytes of data were generated every day in 2012, according to IBM, and by some estimates, 75% of data are unstructured. Data sources that drive tools for investors are diverse and depend on the vendor of the analytics. Some vendors allow users to hand-pick data and custom aggregate it. A few examples of data sources for text analytics are news feeds, select blogs, social media data, RSS (rich site summary) feeds, customer relationship management (CRM) data, and audio and TV news transcripts, such as CNBC’s Squawk Box transcripts. News analytics have been used for years in equity investing, but now, investors are applying these tools in global macro strategies and foreign exchange (FX) trading as well as in commodities and fixed-income investing. Early adopters include quantitative hedge funds in the United States and United Kingdom. Machine learning capabilities are getting better at interpreting and almost understanding what news may mean, although many pitfalls still exist. Most news analytics tools use sentiment analysis algorithms that work with a simple scoring mechanism. Using natural language processing, the algorithm counts the number of positive words and the number of negative words in a text and then assesses which company name appears most in the text. The algorithm assigns a positive or negative score to the text, often including a relevance or probability score for the different entities. It then aggregates this data over the whole news flow and gives users an indication of whether certain companies or terms are trending positive or negative. Some tools score news sentiment and present it as a time series, measure the volume of media coverage, or capture deviations in media coverage that can be telling for investors. Other tools define and track entity relationships in massive textual datasets. The focus of news analytics tools is no longer on speed or reducing latency, according to Armando Gonzalez, president and CEO of RavenPack, a provider of news analytics for quantitative finance applications. “It’s about developing sustainable alpha or verifiable risk management strategies from unstructured data,” he says. “Can users reliably extract a durable signal from the vast amount of news and social content out there that lives for hours, days, weeks, and ideally months?”

Arabic Audio News Retrieval System Using Dependent Speaker Mode, Mel Frequency Cepstral Coefficient and Dynamic Time Warping Techniques

Recently, audio data has increasingly becomes one of the prevalent source of information, especially after the exponential growth of using Internet, digital libraries systems and digital mobile devices. The currently massive amount of audio data stimulates working on developing custom audio retrieval tools to facilitate the audio retrieval tasks. The most familiar audio retrieval systems are based on searching using keyword, title or authors. This study presents the feasibility of using MEL Frequency Cepstral Coefficients (MFCCs) to extract features and Dynamic Time Warping (DTW) to compare the test patterns for Arabic audio news. The study proposes and implements architecture for content based audio retrieval system that is dedicated for the Arabic Audio News. The proposed architecture (ARANEWS) utilizes automatic speech recognition for isolated Arabic keyword speech mode; template based automatic speech recognition approach, MFCCs and DTW. ARANEWS presents a style of retrieval system that based on modeling signal waves and measuring the similarity between features that are extracted from spoken queries and spoken keywords. One of the major components that compose ARANEWS system is feature Database (ARANEWSDB). ARANEWSDB stores the extracted features (MFCCs) from the spoken keywords that are prepared to retrieve Arabic audio news. ARANEWS supports using Query by Humming (QBH) and Query by Example (QBE) instead of using query by text.

Developing an Audio News System Based on Android

With the development of the technology of mobile communication, smartphones have become one of the most popular ways that people get information. However some restrictions such as the screen size, ambient brightness etc. still cause some troubles to read news by smartphones. We based on Android designed an audio news software system by means of the speech synthesis technology which can afford pleasure to listen to information. Using the Andriod technology we developed the smartphone client software which can get the latest information in RSS channels by communicating with the server. Also, it can dynamically manage the RSS channels subscribed by yourself. In the design, we used the techniques of the Android UI framework and component which made the smartphone interface succinct and easy. In order to improve data store efficiency we implemented the data modification and store by transforming between the Json format and the Java object. Based on the iFLY mobile speech platform we developed the audio news player. The function of information automatic acquisition in the server made it possible that smartphones can get the latest information of the subscription channels.

Effects of the rate of computer-mediated speech on emotion-related subjective and physiological responses

In this paper, we describe the results of a psychophysiological study on user's judgements on, and physiological responses to, audio news, which were presented on computer with a fast and slow reading rate. Several effects of condition, age, gender, level of education and level of computer-user experience on the evaluation of the understandability, valence, arousal and interest of the news, as well as on electrodermal and facial muscle activity were found. For example, the fast news was judged as more arousing, but the slow news as more understandable. The younger subjects judged the fast news as more positive and interesting, whereas the opposite was true for older subjects. The results have several methodological and practical implications on presenting and studying speech information in computer systems, such as speech interfaces and news services, given the possibilities afforded by modern technology to present multimodal information effectively and adapt the information and/or interfaces to fit the characteristics of the user (e.g. age).

Emotion-related effects of speech rate and rising vs. falling background music melody during audio news: the moderating influence of personality

We examined the personality-related differences in people’s emotional and other responses to news messages with a slow vs. a fast speech rate and a rising vs. a falling background music melody. Personality was measured with the Behavioural Inhibition System (BIS)/Behavioural Activation System (BAS) scales and the Zuckerman–Kuhlman Personality Questionnaire. Physiological parameters studied were electrodermal activity (EDA), pulse transit time, and interbeat intervals. Several findings consistent with the similarity-attraction theory emerged. For example, subjects scoring high on the BAS, Activity, and Aggression-Hostility dimensions reacted more positively to the news with a fast compared to a slow speech rate. The rising-melody news also elicited higher EDA than the falling-melody news among high BAS scorers. The results suggest that users may be attracted to media messages with audio characteristics manifesting emotions or a personality similar to their own.

Emotion-Related Responses to Audio News with Rising versus Falling Background Tone Sequences

We examined the emotional effects of (a) a rising versus a falling chromatic tone sequence in the background of audio news and (b) foreground versus background diatonic and chromatic tone sequences. In experiment one, 26 participants rated audio news messages with rising and falling chromatic background tone sequences on the valence and arousal dimensions. Cardiac activity, electrodermal activity (EDA), and facial muscle activity were also recorded continuously. In experiment two, 24 participants rated six plain tone sequences ( i.e., rising and falling chromatic, major, and minor) and six news messages with the aforementioned tone sequences mixed in the background on the valence and arousal dimensions. In experiment 1, both self-reported arousal and physiological arousal as measured by EDA were higher during the news with a rising-tone sequence compared to those with a falling-tone sequence. In experiment 2, rising-tone sequences prompted both higher arousal and pleasantness ratings. However, the responses were moderated by the type of listening task: foreground listening prompted responses related to musical connotations ( i.e., major tone sequences were rated as most pleasant and minor as most unpleasant), whereas background listening prompted responses dependent on the emotional congruence between the news messages and tone sequences ( i.e., the minor mode versions were rated as most pleasant and the major mode versions as most unpleasant). In addition, level of education-, music listening frequency-, and age-related differences in the responses were found and are discussed.

Information Retrieval from Unsegmented Broadcast News Audio

This paper describes a system for retrieving relevant portions of broadcast news shows starting with only the audio data. A novel method of automatically detecting and removing commercials is presented and shown to increase the performance of the system while also reducing the computational effort required. A sophisticated large vocabulary speech recogniser which produces high-quality transcriptions of the audio and a window-based retrieval system with post-retrieval merging are also described.

A system for the retrieval of Italian broadcast news

This paper presents a prototype for the retrieval of Italian broadcast news, which has been developed at ITC-irst. The architecture employs a speech recognition engine for the automatic transcription of audio news. Moreover, it features document indexing based on part-of-speech tagging of text coupled with morphological analysis, and query expansion exploiting the Italian WordNet thesaurus. Query-document matching is based on a statistical term weighting scheme. The system was tested on a 203-story collection of audio news, augmented with 9500 newspaper articles. The evaluation was based on a “known item” retrieval task and aimed at evaluating the impact of speech recognition errors and query expansion on retrieval performance.

Synthetic News Radio

This paper describes a system that uses speech recognition and clustered text news stories to automatically find story boundaries in an audio news broadcast and provides a semantic representation that can match audio news stories of similar content. This system creates a personal, synthetic newscast by extracting stories, based on user interests, from multiple hourly newscasts and then reassembling them into a single recording at the end of the day. Interaction is via graphical and telephone-based interfaces, with newscasts delivered over a local area network or to wireless audio pagers.