arXiv AI
Jul 15
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
arXiv:2607. 13013v1 Announce Type: new Abstract: Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time.
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps.
Related stories
arXiv AI
Jun 10
Whisfusion: Parallel ASR Decoding with Masked Diffusion
arXiv:2508. 07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length.
arXiv AI
Jun 10
Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation
arXiv:2606. 10368v1 Announce Type: cross Abstract: Speech-to-text (S2T) systems for recognition (ASR) and translation (S2TT) typically generate discrete text tokens.
arXiv AI
Jul 9
Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
arXiv:2607. 06831v1 Announce Type: cross Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio.
arXiv AI
Jun 19
Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation
arXiv:2606. 20457v1 Announce Type: cross Abstract: Classifier guidance is a way to control diffusion generation by using a noise-conditioned classifier to steer the sampling process toward a target class.
arXiv AI
Jun 30
Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
arXiv:2605. 13087v2 Announce Type: replace-cross Abstract: Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance.
arXiv Machine Learning
Aug 4
Latent Softmax for Data-Efficient Phoneme-Based Multilingual ASR Across Tonal and Non-Tonal Languages
arXiv:2608. 01281v1 Announce Type: cross Abstract: Phoneme-based multilingual automatic speech recognition (ASR) can share acoustic evidence across languages more directly than language-specific subword modeling.
arXiv AI
Jun 3
EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement
arXiv:2606. 02739v1 Announce Type: cross Abstract: Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to support both understanding and generation.
arXiv AI
Jul 2
Adaptive Perturbation Selection for Contrastive Audio Decoding
arXiv:2607. 00247v1 Announce Type: cross Abstract: Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors.
arXiv Machine Learning
Jul 23
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
arXiv:2607. 20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks.
arXiv Machine Learning
Jun 4
Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers
arXiv:2606. 04678v1 Announce Type: new Abstract: End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without training a larger model.
arXiv AI
Jul 13
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
arXiv:2607. 09134v1 Announce Type: cross Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity.