# How AI Predicts Who Will Speak Next in a Conversation > IBM's patent describes a system that uses neural networks to analyze speech patterns and intentions to predict which person will talk next in a conversation. - **Patent:** US 11645473 - **Original title:** End-of-turn detection in spoken dialogues - **Owner:** International Business Machines Corp - **Granted:** 2023 - **Status:** Active - **Times cited:** 0 - **Field:** ai_ml, telecommunications, consumer_electronics ## What it does This system uses a neural network to monitor a conversation between two people and figure out who is likely to speak next. It does this by simultaneously analyzing two things: the speaker's 'intention' (like whether they are asking a question or making a statement) and the 'turn type' (like whether they are trying to hold the floor or are about to switch speakers). By combining these predictions using a joint loss function, the system can determine if the first person will keep talking or if the second person will jump in. For example, if the system detects a rising pitch at the end of a sentence (an acoustic cue) and identifies the intention as a question, it can predict a turn switch to the other person. ## What it does NOT cover - Does not cover systems that only look at text transcripts without analyzing acoustic cues like pitch or speaking rate. - Does not cover simple rule-based systems that rely solely on silence duration to detect turn-taking. - Does not cover systems that predict the content of the next sentence, only the identity of the next speaker. ## The clever bit The innovation lies in training a single neural network to jointly optimize two different tasks—intention recognition and turn-type detection—rather than treating them as separate, sequential steps. ## Real-world examples 1. Smart home voice assistants 2. Automated customer service phone bots 3. Real-time speech-to-text transcription software ## Why it matters Managing natural conversation flow is a major hurdle for voice assistants like Siri or Alexa, which often interrupt users or stop listening too early. By accurately predicting turn-taking, this technology aims to make human-computer interactions feel more fluid and less robotic. It is part of a broader effort to move beyond simple keyword recognition into true conversational understanding. ## Frequently asked questions ### What does How AI Predicts Who Will Speak Next in a Conversation cover? IBM's patent describes a system that uses neural networks to analyze speech patterns and intentions to predict which person will talk next in a conversation. ### Who owns patent US 11645473? International Business Machines Corp owns this patent, granted in 2023. ### When does this patent expire? This patent is expected to expire on May 9, 2043, when the invention enters the public domain. ### What problem does this patent solve? Managing natural conversation flow is a major hurdle for voice assistants like Siri or Alexa, which often interrupt users or stop listening too early. By accurately predicting turn-taking, this technology aims to make human-computer interactions feel more fluid and less robotic. It is part of a broader effort to move beyond simple keyword recognition into true conversational understanding. ### What does this patent NOT cover? Does not cover systems that only look at text transcripts without analyzing acoustic cues like pitch or speaking rate. **Full plain-English explainer:** https://patentbrief.org/patent/us/11645473/palm-pathways-language-model **Original patent:** https://patents.google.com/patent/US11645473 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How Smart Speakers Know You're Talking to Them After a Command](https://patentbrief.org/patent/us/11361763/detecting-system-directed-speech) — This patent describes how a smart speaker system can tell if follow-up speech is meant for it, even without a "wake word," by analyzing voice activity and partial speech recognition results using an AI model. - [How Voice Assistants Distinguish Speakers After a Wakeword](https://patentbrief.org/patent/us/10923111/speech-detection-and-speech-recognition) — This patent describes a method for voice assistants to better understand who is speaking after a 'wakeword' by comparing voice characteristics to improve speech recognition accuracy, especially in multi-speaker environments. - [How Voice Assistants Know When You've Finished Talking](https://patentbrief.org/patent/us/10121471/language-model-speech-endpointing) — This patent describes a method for speech recognition systems to accurately detect the end of a spoken phrase by considering multiple interpretations of the audio and how much silence each interpretation suggests. - [How Voice Assistants Listen for More Commands Without a Wake Word](https://patentbrief.org/patent/us/10847149/speech-based-attention-span-for-voice-user-interface) — This patent describes how a voice assistant can keep listening for follow-up commands after an initial request, without needing you to say its wake word again, based on the type of command you just gave. - [How Voice Assistants Change Their Speech Based on How You Talk](https://patentbrief.org/patent/us/10276149/dynamic-text-to-speech-output) — This patent describes a system where a voice-controlled device adjusts its text-to-speech output characteristics, like speed or tone, based on the user's speaking habits or current situation, making responses feel more natural and personalized.