PulseAugur
EN
LIVE 08:29:53
Italiano(IT) 🧠 # Dessa di # Block impara a conversare da sole voci, senza testo né modelli preaddestrati, secondo il team. Ascolta mentre parla: pause, risate e intonazione

New AI Model 'Dessa' Learns Conversation from Audio Only

By PulseAugur Editorial · [1 sources] ·

A new AI model named Dessa is being developed by a team that claims it can learn to converse solely from audio, without relying on text or pre-trained models. This approach focuses on mimicking human speech patterns, including pauses, laughter, and intonation, to achieve naturalistic conversation. AI

IMPACT This audio-first conversational AI could lead to more natural human-computer interactions and new applications in voice-based interfaces.

RANK_REASON The item describes a novel research approach to AI model training, focusing on audio-only learning for conversational abilities. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New AI Model 'Dessa' Learns Conversation from Audio Only

How we ranked this

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a novel research approach to AI model training, focusing on audio-only learning for conversational abilities. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 Italiano(IT) · [email protected] ·

    🧠 # Dessa di # Block learns to converse on its own, without text or pre-trained models, according to the team. Listen as it speaks: pauses, laughter, and intonation

    🧠 # Dessa di # Block impara a conversare da sole voci, senza testo né modelli preaddestrati, secondo il team. Ascolta mentre parla: pause, risate e intonazione entrano nella conversazione. 👉 I dettagli: https:// lnkd.in/p/dKpi-c8n ___ ✉️ 𝗦𝗲 𝘃𝘂𝗼𝗶 𝗿𝗶𝗺𝗮𝗻𝗲𝗿𝗲 𝗮𝗴𝗴𝗶𝗼𝗿𝗻𝗮𝘁𝗼/𝗮 𝘀𝘂 𝗾𝘂𝗲𝘀𝘁𝗲 𝘁𝗲…

    LINKS linkedin.com/…/alessiopomaro_block-dessa-… alessiopomaro.it

RELATED ENTITIES

RELATED TOPICS