NewsPod: Automatic and Interactive News Podcasts

TL;DR

NewsPod is an innovative system that automatically generates interactive news podcasts using advanced NLP and TTS, featuring segmented conversations with distinct voices and listener interaction capabilities.

Contribution

This work introduces NewsPod, a novel system that creates engaging, interactive news podcasts with distinct voices and user interaction, advancing automated media generation.

Findings

80% of participants preferred NewsPod over baseline

Participants expressed willingness to use the system in the future

Validated through two usability studies

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.