Markdown source

Speech-to-Speech Model Research at Google DeepMind

Conference Context

Session Description

Most voice interfaces today are built as a 3-way cascade system (ASR/LLM/TTS). While functional, this cascaded approach introduces latency bottlenecks, strips away non-verbal nuance, and limits emotion-aware, multi-turn dialogue. Today, we are witnessing a profound shift toward native speech-to-speech models that process audio natively from end to end. In this session, we’ll explore the exciting paradigm at Google DeepMind to train speech-to-speech models for real-time voice agents. We will cover the high-level product and research challenges of building voice agents that feel truly conversational, optimizing for fluid turn-taking and low latency while maintaining enterprise-grade intelligence.

Media Evidence

No related AI Engineer channel video found yet.

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

No linked video, transcript, or slide source has been attached yet.

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Transcript Status

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

People

Notes

Synthesis

Synthesized Breakdown

Speech-to-Speech Model Research at Google DeepMind ## Conference Context - Date/time: 2026-06-29 · 11:10am-11:30am - Track/room: Voice & Realtime AI · Track 6 - Speaker(s): Valeria Wu Fon, Tom Ouyang - Session type/status: session · confirmed - Track: Voice & Realtime AI - Room: Track 6 - Session type: session - Status: confirmed ## Session Description Most voice interfaces today are built as a 3-way cascade system (ASR/LLM/TTS). While functional, this cascaded approach introduces latency bottlenecks, strips away non-verbal nuance, and limits emotion-aware, multi-turn dialogue. Today, we are witnessing a profound shift toward native speech-to-speech models that process audio natively from end to end. In this session, we’ll explore the exciting paradigm at Google DeepMind to train speech-to-speech models for real-time voice agents.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.