NewsPod: Automatic and Interactive News Podcasts
This work addresses the need for more accessible and interactive news consumption for general audiences, though it is incremental as it builds on existing NLP and TTS technologies.
The authors tackled the problem of automatically generating engaging news podcasts by introducing NewsPod, which structures news segments as interactive Q&A conversations with distinct voices and allows listener questions, resulting in 80% of participants preferring it over a baseline and expressing intent to use it.
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.