pith. sign in

arxiv: 2505.17060 · v1 · pith:4WFUSRLDnew · submitted 2025-05-17 · 💻 cs.CL · cs.AI

SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation

classification 💻 cs.CL cs.AI
keywords salmonn-omnifull-duplexspeechperformancesystemsaudiobarge-incancellation
0
0 comments X
read the original abstract

In order to enable fluid and natural human-machine speech interaction, existing full-duplex conversational systems often adopt modular architectures with auxiliary components such as voice activity detectors, interrupters, conversation state predictors, or multiple LLMs. These systems, however, suffer from error accumulation across modules and struggle with key challenges such as context-dependent barge-in and echo cancellation. Recent approaches, most notably Moshi, simplify the pipeline by injecting audio codecs into the token space of a single LLM. However, such methods still incur significant performance degradation when operating on the speech rather than text modality. In this paper, we introduce SALMONN-omni, the first single, standalone full-duplex speech LLM that operates without audio codecs in its token space. It features a novel dynamic thinking mechanism within the LLM backbone, enabling the model to learn when to transition between speaking and listening states. Experiments on widely used benchmarks for spoken question answering and open-domain dialogue show that SALMONN-omni achieves at least 30\% relative performance improvement over existing open-source full-duplex models and performs highly competitively to half-duplex and turn-based systems, despite using substantially less training data. Moreover, SALMONN-omni demonstrates strong performance in complex conversational scenarios, including turn-taking, backchanneling, echo cancellation and context-dependent barge-in, with further improvements achieved through reinforcement learning. Some demo conversations between user and SALMONN-omni are provided in the following repository https://github.com/bytedance/SALMONN.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue

    cs.CL 2026-05 unverdicted novelty 7.0

    Channel fusion gives better semantic grounding and QA performance in full-duplex LLM dialogue but is vulnerable to context corruption during interruptions, while cross-attention routing is more robust at the cost of w...

  2. The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

    eess.AS 2026-03 unverdicted novelty 7.0

    FLAIR enables spoken dialogue AI to conduct continuous latent reasoning while perceiving speech through recursive latent embeddings and an ELBO-based finetuning objective.

  3. Game-Time: Evaluating Temporal Dynamics in Spoken Language Models

    eess.AS 2025-09 unverdicted novelty 7.0

    Game-Time Benchmark shows spoken language models handle basic tasks but degrade sharply under temporal constraints like tempo adherence and synchronized responses.

  4. PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding

    eess.AS 2026-05 unverdicted novelty 6.0

    PlanRAG-Audio introduces a planning-based retrieval-augmented generation approach that lets large audio language models handle long recordings by selectively retrieving query-relevant information rather than processin...

  5. Adaptive Perturbation Selection for Contrastive Audio Decoding

    cs.SD 2026-06 unverdicted novelty 5.0

    Adaptive selection among a library of audio perturbations in contrastive decoding produces task-dependent accuracy gains, including +4.3% on an existence task via a hidden-state selector.

  6. Endpoint Anticipation for Low-Latency Spoken Dialogue

    eess.AS 2026-06 unverdicted novelty 5.0

    A speech-based model forecasts conversation turn endpoints up to 2.56 seconds ahead to enable lower-latency spoken dialogue via speculative LLM and TTS execution.

  7. DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction

    cs.HC 2026-06 unverdicted novelty 5.0

    DuplexOmni achieves real-time full-duplex multimodal interaction by separating an interaction layer from a pluggable thinking layer, supported by a Writer-Director pipeline for continuous-interaction training data.

  8. PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding

    eess.AS 2026-05 unverdicted novelty 4.0

    PlanRAG-Audio introduces planning-based retrieval-augmented generation to improve accuracy and stability of long-form audio understanding in LALMs by decoupling model input from raw audio duration.

  9. The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

    eess.AS 2026-03 unverdicted novelty 4.0

    FLAIR enables simultaneous latent reasoning during speech input in full-duplex dialogue models via recursive latent embeddings and an ELBO-based training objective without added latency.