Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models

• URL: http://arxiv.org/abs/2604.15383v1
• Date: Thu, 16 Apr 2026 02:30:41 GMT
• Title: Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models
• Abstract summary: Large audio-language models (LALMs) generalize across speech, sound, and music.<n> unified decoders can exhibit a emphtemporal smoothing bias<n>We propose emphTemporal Contrastive Decoding (TCD), a training-free decoding method for unified LALMs.
• Score: 56.91801348360746
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be underutilized in favor of temporally smooth context that is better supported by language priors, leading to less specific audio-grounded outputs. We propose \emph{Temporal Contrastive Decoding} (TCD), a training-free decoding method for unified LALMs that mitigates this effect at inference time. TCD constructs a temporally blurred slow-path view by smoothing the input waveform and re-encoding it, then contrasts next-token logits from the original and slow-path views. The contrastive signal is applied as a token-level logit update restricted to a small candidate set. A self-normalized stability score sets the blur window and update scale, and a step-wise gate based on uncertainty and audio reliance activates the update only when needed. Experiments on MMAU and AIR-Bench show consistent improvements on strong unified LALMs. We further conduct ablations and an architectural applicability study to analyze the contributions of key components and how TCD behaves across large audio-language model designs.

Related papers

• TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models [58.80225070159013]
  Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify.<n>We present TEMPO, the first unified model to handle audio, speech, and music timestamping tasks.
  arXiv  Detail & Related papers  (2026-08-30T19:49:21Z)
• Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models [51.75139461584678]
  Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order.<n>We propose an instruction-level framework that uses audio-aware large language models as fine-grained judges to verify target event presence and temporal relations.<n>Experiments show that our method improves event completeness, temporal ordering, and joint instruction-following accuracy across existing benchmarks and S3Bench, while maintaining audio quality.
  arXiv  Detail & Related papers  (2026-07-15T03:13:06Z)
• AudioMosaic: Contrastive Masked Audio Representation Learning [53.52371029884106]
  We introduce textbfAudioMosaic, a contrastive learning-based audio encoder for general audio understanding.<n>AudioMosaic constructs positive pairs by applying structured time-frequency masking to spectrogram patches.<n>Experiments show that AudioMosaic achieves state-of-the-art performance on several standard audio benchmarks.
  arXiv  Detail & Related papers  (2026-05-14T00:56:51Z)
• STDec: Spatio-Temporal Stability Guided Decoding for dLLMs [49.55447757907809]
  Large Diffusion Language Models (dLLMs) have achieved rapid progress, viewed as a promising alternative to the autoregressive paradigm.<n>Most dLLM decoders still adopt a global confidence threshold, and do not model local context from neighboring decoded states or temporal consistency of predicted token IDs.<n>We observe strong stability neartemporal stability in dLLM decoding, and our approach includes spatial-aware decoding and temporal-aware decoding.
  arXiv  Detail & Related papers  (2026-04-07T18:13:31Z)
• TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling [52.519745466772825]
  Text-speech joint spoken language modeling aims at natural and intelligent speech-based interactions.<n>TASTE produces speech tokens that align in lengths with their textual counterparts.<n>We propose TASTE-S, a streamable extension of TASTE suitable for real-time usage.
  arXiv  Detail & Related papers  (2026-03-12T18:13:48Z)
• Frame-Level Internal Tool Use for Temporal Grounding in Audio LMs [48.50855715191533]
  Large audio language models are increasingly used for complex audio understanding tasks.<n>They struggle with temporal tasks that require precise temporal grounding, such as word alignment and speaker diarization.<n>We propose frame-level internal tool use, a method that trains audio LMs to use their own internal audio representations to perform temporal grounding directly.
  arXiv  Detail & Related papers  (2026-02-10T19:19:52Z)
• Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization [27.32235541083431]
  We introduce DyCAST, a Dynamic Character-Aligned Speech Tokenizer.<n>DyCAST learns to associate tokens with character-level linguistic units during training.<n>We also introduce a retrieval-augmented decoding mechanism that enhances reconstruction without increasing fidelity.
  arXiv  Detail & Related papers  (2026-01-30T16:58:40Z)
• From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data [55.2480439325792]
  Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs.<n>These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks.<n>We propose a data generation framework that produces contrastive-like training data, designed to enhance ALLMs' ability to differentiate between present and absent sounds.
  arXiv  Detail & Related papers  (2025-05-26T16:08:41Z)
• VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment [101.2489492032816]
  VALL-E R is a robust and efficient zero-shot Text-to-Speech system. This research has the potential to be applied to meaningful projects, including the creation of speech for those affected by aphasia.
  arXiv  Detail & Related papers  (2024-06-12T04:09:44Z)
• Autoregressive Diffusion Transformer for Text-to-Speech Synthesis [39.32761051774537]
  We propose encoding audio as vector sequences in continuous space $mathbb Rd$ and autoregressively generating these sequences. High-bitrate continuous speech representation enables almost flawless reconstruction, allowing our model to achieve nearly perfect speech editing.
  arXiv  Detail & Related papers  (2024-06-08T18:57:13Z)

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.