ABSTRACT
AudiLens is a large-language model (LLM)-based audience simulator for public speech practice that allows speakers to generate and configure a group of generated audiences, and use them to receive feedback on their speech during and after the practice in multiple aspects. AudiLens leverages the capability of LLMs in being able to generate a diverse set of personas and being able to simulate human behavior, and provide flexibility to the speaker in terms of practicing their speech with multiple sets of audience groups in multiple speech formats. We demonstrate the use of AudiLens in two scenarios—giving a tutorial and debating.
- Gati Aher, Rosa I Arriaga, and Adam Tauman Kalai. 2022. Using large language models to simulate multiple humans. arXiv e-prints (2022), arXiv–2208.Google Scholar
- Gati V Aher, Rosa I Arriaga, and Adam Tauman Kalai. 2023. Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning. PMLR, 337–371.Google Scholar
- J Maxwell Atkinson. 1984. 15. Public speaking and audience responses: some techniques for inviting applause. (1984).Google Scholar
- Steven A Beebe and Susan J Beebe. 2009. e: Public Speaking: An Audience-Centered Approach, 11/e. (2009).Google Scholar
- Denis McQuail. 1997. Audience analysis. Sage.Google Scholar
- Joon Sung Park, Lindsay Popowski, Carrie Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2022. Social simulacra: Creating populated prototypes for social computing systems. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology. 1–18.Google ScholarDigital Library
- Bao Truong, Trung-Nghia Le, Khanh-Duy Le, Minh-Triet Tran, and Tam V Nguyen. 2022. Public Speaking Simulator with Speech and Audience Feedback. In 2022 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct). IEEE, 855–858.Google Scholar
- Department of Communication University of Pittsburgh. 2015. Audience Analysis. https://www.comm.pitt.edu/oral-comm-lab/audience-analysis.Google Scholar
- Eunkyong Lee Yook. 2004. Any Questions? Knowing the Audience through Question Types.Communication Teacher 18, 3 (2004), 91–93.Google Scholar
- Juan Diego Zapata-Rivera and Irvin R Katz. 2014. Keeping your audience in mind: Applying audience analysis to the design of interactive score reports. Assessment in Education: Principles, Policy & Practice 21, 4 (2014), 442–463.Google ScholarCross Ref
Index Terms
- AudiLens: Configurable LLM-Generated Audiences for Public Speech Practice
Recommendations
Recognition and Feedback of Vowel Utterance with a Good Mouth Shape Based on Sensing Platysma Muscle Bulging
AH '18: Proceedings of the 9th Augmented Human International ConferenceIn public speaking, speakers are evaluated on verbal delivery and nonverbal delivery, and in particular, the mouth shape has an important role to support both of these. The mouth shape is mainly set during vowel utterance. We define the mouth shape, ...
Intelligibility enhancement of HMM-generated speech in additive noise by modifying Mel cepstral coefficients to increase the glimpse proportion
This paper describes speech intelligibility enhancement for Hidden Markov Model (HMM) generated synthetic speech in noise. We present a method for modifying the Mel cepstral coefficients generated by statistical parametric models that have been trained ...
Comments