Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers

• URL: http://arxiv.org/abs/2510.04577v1
• Date: Mon, 06 Oct 2025 08:26:55 GMT
• Title: Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers
• Authors: Juncheng Wang, Chao Xu, Cheng Yu, Zhe Hu, Haoyu Xie, Guoqi Yu, Lei Shang, Shujun Wang,
• Abstract summary: We propose a novel LM-based framework that employs multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning.<n>We show that Siren outperforms both existing LM-based and diffusion-based T2A systems, achieving state-of-the-art results.
• Score: 24.722647001947923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While language models (LMs) paired with residual vector quantization (RVQ) tokenizers have shown promise in text-to-audio (T2A) generation, they still lag behind diffusion-based models by a non-trivial margin. We identify a critical dilemma underpinning this gap: incorporating more RVQ layers improves audio reconstruction fidelity but exceeds the generation capacity of conventional LMs. To address this, we first analyze RVQ dynamics and uncover two key limitations: 1) orthogonality of features across RVQ layers hinders effective LMs training, and 2) descending semantic richness in tokens from deeper RVQ layers exacerbates exposure bias during autoregressive decoding. Based on these insights, we propose Siren, a novel LM-based framework that employs multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning. Extensive experiments demonstrate that Siren outperforms both existing LM-based and diffusion-based T2A systems, achieving state-of-the-art results. By bridging the representational strengths of LMs with the fidelity demands of audio synthesis, our approach repositions LMs as competitive contenders against diffusion models in T2A tasks. Moreover, by aligning audio representations with linguistic structures, Siren facilitates a promising pathway toward unified multi-modal generation frameworks.

Related papers

• DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation [23.171175300622675]
  We propose a unified framework for controllable human-centric audio-video generation.<n>DreamID- Omni achieves comprehensive state-of-the-art performance across video, audio, and audio-visual consistency.<n>We will release our code to bridge the gap between academic research and commercial-grade applications.
  arXiv  Detail & Related papers  (2026-02-12T16:41:52Z)
• GMS-CAVP: Improving Audio-Video Correspondence with Multi-Scale Contrastive and Generative Pretraining [64.72014392166625]
  GMS-CAVP is a novel framework that combines Multi-Scale Video-Audio Alignment and Multi-Scale Spatial-Temporal Diffusion-based pretraining objectives.<n>First, GMS-CAVP introduces a multi-scale contrastive learning strategy that captures semantic and temporal relations across varying granularities.<n>Second, we go beyond traditional contrastive learning by incorporating a diffusion-based generative objective, enabling modality translation and synthesis between video and audio.
  arXiv  Detail & Related papers  (2026-01-27T13:43:32Z)
• GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model [35.12859489567766]
  We present GenTSE, a two-stage decoder-only generative LM approach for TSE.<n> separating semantics and acoustics stabilizes decoding and yields more faithful, content-aligned target speech.<n>Experiments on Libri2Mix show that GenTSE surpasses previous LM-based systems in speech quality, intelligibility, and speaker consistency.
  arXiv  Detail & Related papers  (2025-12-24T06:13:02Z)
• Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses [71.34350093068473]
  This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR)<n>Our framework, DualHyp, empowers a large language model (LLM) to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition (VSR) models.<n>Our framework attains up to 57.7% error rate gain on the LRS2 benchmark over standard ASR baseline, contrary to single-stream GER approaches that achieve only 10% gain.
  arXiv  Detail & Related papers  (2025-10-15T08:27:16Z)
• Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations [26.938560887095658]
  Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss.<n>We propose QTTS, a novel TTS framework built upon our new audio, QDAC.<n>Our experiments demonstrate that the proposed framework achieves higher synthesis quality and better preserves expressive content compared to baseline.
  arXiv  Detail & Related papers  (2025-07-16T12:47:09Z)
• DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations [62.00227663434538]
  DRVOICE-7B establishes new state-of-the-art (SOTA) on OpenAudioBench and Big Bench Audio benchmarks.<n>This paper presents DrVoice, a parallel speech-text voice conversation model based on joint autoregressive modeling.
  arXiv  Detail & Related papers  (2025-06-11T02:57:22Z)
• Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought [58.321044666612174]
  Vad-R1 is an end-to-end MLLM-based framework for Video Anomaly Reasoning.<n>We design a Perception-to-Cognition Chain-of-Thought (P2C-CoT) that simulates the human process of recognizing anomalies.<n>We also propose an improved reinforcement learning algorithm AVA-GRPO, which explicitly incentivizes the anomaly reasoning capability of MLLMs.
  arXiv  Detail & Related papers  (2025-05-26T12:05:16Z)
• FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing [81.3306413498174]
  Movie Dubbing aims to convert scripts into speeches that align with the given movie clip in both temporal and emotional aspects.<n>Existing methods focus primarily on reducing the word error rate while ignoring the importance of lip-sync and acoustic quality.<n>We propose a large language model (LLM) based flow matching architecture for dubbing, named FlowDubber.
  arXiv  Detail & Related papers  (2025-05-02T13:30:19Z)
• MTLM: Incorporating Bidirectional Text Information to Enhance Language Model Training in Speech Recognition Systems [8.971049629873185]
  MTLM is a novel training paradigm that unifies unidirectional and bidirectional manners through 3 training objectives.<n>It supports multiple decoding strategies, including shallow fusion, unidirectional/bidirectional n-best rescoring.<n>Experiments on the LibriSpeech dataset show that MTLM consistently outperforms unidirectional training across multiple decoding strategies.
  arXiv  Detail & Related papers  (2025-02-14T10:21:10Z)
• VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval [8.908777234657046]
  Large-language and vision-language models (LLM/LVLMs) have gained prominence across various domains.<n>Here we propose VideoLights, a novel HD/MR framework addressing these limitations through (i) Convolutional Projection and Feature Refinement modules.<n> Comprehensive experiments on QVHighlights, TVSum, and Charades-STA benchmarks demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-02T14:45:53Z)
• Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion [93.32354378820648]
  We introduce MVSD, a mutual learning framework based on diffusion models. MVSD considers the two tasks symmetrically, exploiting the reciprocal relationship to facilitate learning from inverse tasks. Our framework can improve the performance of the reverberator and dereverberator.
  arXiv  Detail & Related papers  (2024-07-15T00:47:56Z)
• Language Models as Hierarchy Encoders [22.03504018330068]
  We introduce a novel approach to re-train transformer encoder-based LMs as Hierarchy Transformer encoders (HiTs) Our method situates the output embedding space of pre-trained LMs within a Poincar'e ball with a curvature that adapts to the embedding dimension. We evaluate HiTs against pre-trained LMs, standard fine-tuned LMs, and several hyperbolic embedding baselines.
  arXiv  Detail & Related papers  (2024-01-21T02:29:12Z)
• Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation [72.7915031238824]
  Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks. They often suffer from common issues such as semantic misalignment and poor temporal consistency. We propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio.
  arXiv  Detail & Related papers  (2023-05-29T10:41:28Z)
• TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation [61.564874831498145]
  TranSpeech is a speech-to-speech translation model with bilateral perturbation. We establish a non-autoregressive S2ST technique, which repeatedly masks and predicts unit choices. TranSpeech shows a significant improvement in inference latency, enabling speedup up to 21.4x than autoregressive technique.
  arXiv  Detail & Related papers  (2022-05-25T06:34:14Z)
• Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer [29.03463312813923]
  Video denoising aims to recover high-quality frames from the noisy video. Most existing approaches adopt convolutional neural networks(CNNs) to separate the noise from the original visual content. We propose a Dual-stage Spatial-Channel Transformer (DSCT) for coarse-to-fine video denoising.
  arXiv  Detail & Related papers  (2022-04-30T09:01:21Z)
• High-Speed and High-Quality Text-to-Lip Generation [55.20612501355773]
  We propose a novel parallel decoding model for high-speed and high-quality text-to-lip generation (HH-T2L) We predict the duration of the encoded linguistic features and model the target lip frames conditioned on the encoded linguistic features with their duration in a non-autoregressive manner. Experiments conducted on GRID and TCD-TIMIT datasets show that HH-T2L generates lip movements with competitive quality compared with the state-of-the-art AR T2L model DualLip.
  arXiv  Detail & Related papers  (2021-07-14T16:44:04Z)

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.