home.social

#voiceinteraction — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #voiceinteraction, aggregated by home.social.

  1. Discover how the KT148A voice chip is transforming medical devices! This 8-pin IC enables blood glucose meters to announce results, infusion pumps to cut through noise, and rehab equipment to guide patients. Features include 420KByte storage, 2μA static current, PWM-driven speaker, and wide-temperature support. Perfect for medical applications requiring reliability and clarity. #KT148A #VoiceChip #MedicalDevices #VoiceInteraction #MedTech #EmbeddedDesign

    linkedin.com/pulse/sound-revol

  2. arxiv.org/pdf/2402.03578 appears to be quite interesting for my work in the #w3c community group for #voiceinteraction and the Open Voice Network #ovon:
    Multi-agent systems boost LLM capabilities via agent collaboration. Challenges include task allocation, reasoning, context & memory management. Explores applications in blockchain systems. #LLMs #MultiAgentSystems #AI #Blockchain

  3. Changes for github.com/w3c/voiceinteractio Improve description of Generative AI elements after the review in the last session on 2024-10-23 of the #w3c #voiceinteraction community group

    section 3
    - added a note about location of components
    section 3.2
    - added differences between Trad #NLU and Gen AI system
    section 3.2.5.2, 3.3.1
    - Added #agenticapplications
    section 3.2.8.2, 3.2.8.4
    - Spearation of usages in Trad NLU and Gen AI
    Figure 3, 4
    - gray out #LLM

    #GenerativeAI

  4. In the #w3c #voiceinteraction community group we are just discussing if personal digital assistants can be called personal if all data is shared with others.

    Any opinions on that?

    #digitalassistant #voicecommunication #conversationalai #privacy #trust

  5. I made some updates to improve the description of #GenerativeAI components.
    Current draft is at w3c.github.io/voiceinteraction

    I was under the impression that dialogs with their description how to cope with input and decide upon the output would only be relevant for traditional #NLU based systems. However, in the #LLM post processing we may also be in the need to make use of, e.g., error dialogs if a call to the LLM could not be established. I still need to think about it.

    #w3c #voiceinteraction

  6. The currently followed architecture of our #w3c community group is still too closely bound to traditional #NLU based #voiceinteraction concepts. While it aimed at including #llm with speech, LLM with multimodality, ... it is potentially not visible enough. We may want to also improve here.

  7. Some first code towards a reference implementation for a framework of intelligent personal assistants from our #w3c community group for #voiceinteraction

    Please, feel invited to comment and contribute.

    voiceinteraction/source/SOURCE.md at master · w3c/voiceinteraction · GitHub
    github.com/w3c/voiceinteractio

    #programming #voiceassistant