Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision

• URL: http://arxiv.org/abs/2503.01879v3
• Date: Thu, 29 May 2025 09:40:51 GMT
• Title: Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision
• Authors: Che Liu, Yingji Zhang, Dong Zhang, Weijie Zhang, Chenggong Gong, Haohan Li, Yu Lu, Shilin Zhou, Yue Lu, Ziliang Gan, Ziao Wang, Junwei Liao, Haipang Wu, Ji Liu, André Freitas, Qifan Wang, Zenglin Xu, Rongjuncheng Zhang, Yong Dai,
• Abstract summary: This work proposes an industry-level omni-modal large language model (LLM) pipeline that integrates auditory, visual, and linguistic modalities.<n>Our pipeline consists of three main components: First, a modular framework enabling flexible configuration of various encoder-LLM-decoder architectures.<n>Second, a lightweight training strategy that pre-trains audio-language alignment on the state-of-the-art vision-language model Qwen2.5-VL.<n>Third, an audio synthesis pipeline that generates high-quality audio-text data from diverse real-world scenarios.
• Score: 50.23246260804145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work proposes an industry-level omni-modal large language model (LLM) pipeline that integrates auditory, visual, and linguistic modalities to overcome challenges such as limited tri-modal datasets, high computational costs, and complex feature alignments. Our pipeline consists of three main components: First, a modular framework enabling flexible configuration of various encoder-LLM-decoder architectures. Second, a lightweight training strategy that pre-trains audio-language alignment on the state-of-the-art vision-language model Qwen2.5-VL, thus avoiding the costly pre-training of vision-specific modalities. Third, an audio synthesis pipeline that generates high-quality audio-text data from diverse real-world scenarios, supporting applications such as Automatic Speech Recognition and Speech-to-Speech chat. To this end, we introduce an industry-level omni-modal LLM, Nexus. Extensive experiments validate the efficacy of our pipeline, yielding the following key findings:(1) In the visual understanding task, Nexus exhibits superior performance compared with its backbone model - Qwen2.5-VL-7B, validating the efficiency of our training strategy. (2) Within the English Spoken Question-Answering task, the model achieves better accuracy than the same-period competitor (i.e, MiniCPM-o2.6-7B) in the LLaMA Q. benchmark. (3) In our real-world ASR testset, Nexus achieves outstanding performance, indicating its robustness in real scenarios. (4) In the Speech-to-Text Translation task, our model outperforms Qwen2-Audio-Instruct-7B. (5) In the Text-to-Speech task, based on pretrained vocoder (e.g., Fishspeech1.4 or CosyVoice2.0), Nexus is comparable to its backbone vocoder on Seed-TTS benchmark. (6) An in-depth analysis of tri-modal alignment reveals that incorporating the audio modality enhances representational alignment between vision and language.

Related papers

• Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model [76.06585781346601]
  Speech language models (Speech LMs) enable end-to-end speech-text modelling within a single model.<n>The choice of speech-text jointly decoding paradigm plays a critical role in performance, efficiency, and alignment quality.
  arXiv  Detail & Related papers  (2025-06-04T23:53:49Z)
• VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model [70.25062476543091]
  VITA-Audio is an end-to-end large speech model with fast audio-text token generation.<n>MCTP module efficiently generates multiple audio tokens within a single model forward pass.<n>Four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality.
  arXiv  Detail & Related papers  (2025-05-06T17:59:53Z)
• GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM [42.93855899824886]
  We propose a text-to-speech generation approach optimized via a novel dual-branch ArchiTecture (GOAT-TTS)<n>GOAT-TTS combines a speech encoder and projector to capture continuous acoustic embeddings, enabling bidirectional correlation between paralinguistic features (language, timbre, emotion) and semantic text representations without transcript dependency.<n> Experimental results demonstrate that our GOAT-TTS achieves performance comparable to state-of-the-art TTS models.
  arXiv  Detail & Related papers  (2025-04-15T01:44:56Z)
• Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction [110.38946048535033]
  This paper introduces Step-Audio, the first production-ready open-source solution for speech recognition.<n>Key contributions include: 1) a unified speech-text multi-modal model that achieves unified understanding and generation, with the Step-Audio-Chat version open-sourced; 2) a generative speech data engine that establishes an affordable voice cloning framework and produces the open-sourced lightweight Step-Audio-TTS-3B model through distillation; 3) an instruction-driven fine control system enabling dynamic adjustments across dialects, emotions, singing, and RAP; 4) an enhanced cognitive architecture augmented with tool calling and role-playing abilities to manage complex
  arXiv  Detail & Related papers  (2025-02-17T15:58:56Z)
• Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment [88.72389428177942]
  Ola is an omni-modal language model that achieves competitive performance across image, video, and audio understanding. We aim to make Ola a fully open omni-modal understanding solution to advance future research in this emerging field.
  arXiv  Detail & Related papers  (2025-02-06T18:59:55Z)
• OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis [68.73476738779628]
  name is a two-stage training framework that integrates omnimodal alignment and speech generation. It surpasses state-of-the-art models across omnimodal, vision-language, and speech-language benchmarks. name achieves real-time speech generation with 1s latency at non-autoregressive mode.
  arXiv  Detail & Related papers  (2025-01-08T15:18:09Z)
• ETTA: Elucidating the Design Space of Text-to-Audio Models [33.831803213869605]
  We study the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks.<n>We propose our best model dubbed Elucidated Text-To-Audio (ETTA)<n>ETTA provides improvements over the baselines trained on publicly available data, while being competitive with models trained on proprietary data.
  arXiv  Detail & Related papers  (2024-12-26T21:13:12Z)
• CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models [74.80386066714229]
  We present an improved streaming speech synthesis model, CosyVoice 2. Specifically, we introduce finite-scalar quantization to improve codebook utilization of speech tokens. We develop a chunk-aware causal flow matching model to support various synthesis scenarios.
  arXiv  Detail & Related papers  (2024-12-13T12:59:39Z)
• Visatronic: A Multimodal Decoder-Only Model for Speech Synthesis [13.702423348269155]
  Video-Text to Speech (VTTS) is a speech generation task conditioned on both its corresponding text and video of talking people.<n>We introduce Visatronic, a unified multimodal decoder-only transformer model that embeds visual, textual, and speech inputs into a shared subspace.<n>We show that Visatronic achieves a 4.5% WER, outperforming prior SOTA methods trained only on LRS3.
  arXiv  Detail & Related papers  (2024-11-26T18:57:29Z)
• SONAR: A Synthetic AI-Audio Detection Framework and Benchmark [59.09338266364506]
  SONAR is a synthetic AI-Audio Detection Framework and Benchmark. It aims to provide a comprehensive evaluation for distinguishing cutting-edge AI-synthesized auditory content. It is the first framework to uniformly benchmark AI-audio detection across both traditional and foundation model-based deepfake detection systems.
  arXiv  Detail & Related papers  (2024-10-06T01:03:42Z)
• OmniBench: Towards The Future of Universal Omni-Language Models [63.16606414452612]
  We introduce OmniBench, a novel benchmark designed to rigorously evaluate models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously. Our main findings reveal that most OLMs exhibit critical limitations in instruction-following and reasoning capabilities within tri-modal contexts. To address this gap, we curate an instruction tuning dataset of 84.5K training samples, OmniInstruct, for training OLMs to adapt to multimodal contexts.
  arXiv  Detail & Related papers  (2024-09-23T17:59:05Z)
• Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications [20.842799581850617]
  We consider the task of animating 3D facial geometry from speech signal. Existing works are primarily deterministic, focusing on learning a one-to-one mapping from speech signal to 3D face meshes on small datasets with limited speakers.
  arXiv  Detail & Related papers  (2023-11-30T01:14:43Z)
• Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech [6.243356997302935]
  We introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations from recordings in the target language, which are then used to train a single-speaker acoustic model.
  arXiv  Detail & Related papers  (2023-09-15T09:03:14Z)
• FALL-E: A Foley Sound Synthesis Model and Strategies [0.5599792629509229]
  The FALL-E model employs a cascaded approach comprising low-resolution spectrogram generation, spectrogram super-resolution, and a vocoder. We conditioned the model with dataset-specific texts, enabling it to learn sound quality and recording environment based on text input.
  arXiv  Detail & Related papers  (2023-06-16T12:44:10Z)
• VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation [91.39949385661379]
  VioLA is a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text. We first convert all the speech utterances to discrete tokens using an offline neural encoder. We further integrate task IDs (TID) and language IDs (LID) into the proposed model to enhance the modeling capability of handling different languages and tasks.
  arXiv  Detail & Related papers  (2023-05-25T14:39:47Z)
• VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset [34.38377548121313]
  We propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation.<n>VALOR jointly models relationships of vision, audio and language in an end-to-end manner.<n>It achieves new state-of-the-art performances on series of public cross-modality benchmarks.
  arXiv  Detail & Related papers  (2023-04-17T15:08:15Z)
• Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data [15.658471125219224]
  Multimodal pre-training for audio-and-text has been proven to be effective and has significantly improved the performance of many downstream speech understanding tasks. However, these state-of-the-art pre-training audio-text models work well only when provided with large amount of parallel audio-and-text data. In this paper, we investigate whether it is possible to pre-train an audio-text model with low-resource parallel data.
  arXiv  Detail & Related papers  (2022-04-10T10:25:37Z)
• Contextualized Spoken Word Representations from Convolutional Autoencoders [2.28438857884398]
  This paper proposes a Convolutional Autoencoder based neural architecture to model syntactically and semantically adequate contextualized representations of varying length spoken words. The proposed model was able to demonstrate its robustness when compared to the other two language-based models.
  arXiv  Detail & Related papers  (2020-07-06T16:48:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.