NewsPod: Automatic and Interactive News Podcasts

Abstract

News podcasts are a popular medium to stay informed and dive deep into news topics. Today, most podcasts are handcrafted by professionals. In this work, we advance the state-of-the-art in automatically generated podcasts, making use of recent advances in natural language processing and text-to-speech technology. We present NewsPod, an automatically generated, interactive news podcast. The podcast is divided into segments, each centered on a news event, with each segment structured as a Question and Answer conversation, whose goal is to engage the listener. A key aspect of the design is the use of distinct voices for each role (questioner, responder), to better simulate a conversation. Another novel aspect of NewsPod allows listeners to interact with the podcast by asking their own questions and receiving automatically generated answers. We validate the soundness of this system design through two usability studies, focused on evaluating the narrative style and interactions with the podcast, respectively. We find that NewsPod is preferred over a baseline by participants, with 80% claiming they would use the system in the future.

Impact of Voice Fidelity on Decision Making: A Potential Dark Pattern?

“…While CAs are becoming more frequently used in transactional scenarios, research indicates that monotonous, robotic and unnatural vocal features of TTS negatively impact users' engagement [12,14,25]. This can be addressed by appropriate interaction design and providing a better fit of voice to application domains by diversifying voices to improve user experience [2,3,42,54,66,82]. Indeed, empirical evidence suggests that voices that are enjoyable to listen to can not only delight users but also establish lasting relationship and long-term usage [78].…”

Discord Questions: A Computational Approach To Diversity Analysis in News Coverage

“…Furthermore, beyond the setting of Google News stories, discord questions could be beneficial on the study of long, unfolding news stories (Laban and Hearst, 2017), helping readers form evolving opinions over time. Finally, future work should aim to integrate discord questions into non-standard news interfaces such as chatbots (Laban et al, 2020) or podcasts (Laban et al, 2022b).…”

Exploring Abstractive Text Summarisation for Podcasts: A Comparative Study of BART and T5 Models

“…These models are pre-trained on large amounts of text data and can be fine-tuned on taskspecific datasets to generate summaries that capture the essential content of the source text (Lewis et al, 2019;Xue et al, 2021;Brown et al, 2020) The task of summarising podcasts has gained attention in recent years, with several studies proposing approaches for automated podcast summarisation. Laban et al (2022) proposed an interactive summarisation approach for news podcasts, which allows users to engage with the summarisation process by providing feedback. This approach uses extractive summarisation to select important sen-tences from the podcast transcript and then generates a summary from these sentences.…”