Q&A: Wolf Paulus on the Engineering of Emotion
At the 2019 SpeechTEK Conference (April 29-May 1), Wolf Paulus, Principal Engineer, Technology Futures, Intuit and University of California, Irvine will be exploring "The Engineering of Emotion." Conference Chair Jim Larson interviewed Paulus to get a sneak peek at the session and explore the world of sentiment analysis.
Q: What user emotions can be detected from the text that is spoken or voiced by the user?
A: Basic sentiment or attitude for very negative to very positive can be detected in user input. If the input is less subtle, multiple dimensions of tone like joy, sadness, anger, fear and even frustration and impoliteness can be detected.
Q: What user emotions can be extracted from the user’s voice?
A: Happiness, sadness, anger, and fear can be recognized in a user's voice with some accuracy, especially, if the sample exceeds three seconds.
Q: What other techniques can be used to detect user emotions?
A: Using emotion detection in a user’s facial expressions works with good accuracy but users often reject being “filmed.” Therefore analyzing their voice and text input for sentiment seems is an effective way to gain inside.
Q: How can users make use of detected emotions?
A: In my the talk at SpeechTEK, I explore how we can use tools and techniques (which were developed to detect emotion and sentiment in user input), to validate that the responses we create for CUIs and VUIs, show the intended sentiment or attitude. To make sure the skills or bots we are building responds kindly, considerately and empathically if warranted.
Register for SpeechTEK today to learn more about The Engineering of Emotion.
At the 2019 SpeechTEK Conference (April 29-May 1), Bruce Balentine, design consultant specializing in speech, audio, and multimodal user interfaces, will be presenting "Discoverability in Spoken user Interfaces." Conference Chair Jim Larson interviewed Balentine to get a sneak peek at the session and talk about discoverability.
The 2019 Conversational Interaction Conference emphasized innovative applications using the latest speech technologies, alternative architectures to ease the creation of conversational apps, and best practices for designing speech dialogs.