The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2607. 00986v1 Announce Type: new Abstract: Automatically detecting stress in speech provides an unobtrusive way to gain insights relevant to behavioral research or clinical assessment.
The paper introduces LLM-Anchored Paralinguistic Enrichment (LAPE), a method that enhances language model representations with speech-based paralinguistic cues such as pauses and word elongations. LAPE incorporates three innovations: prosodic event textualization, lexico-prosodic unitization and chunking, and text-anchored paralinguistic fusion using NormGate. Evaluations on the ADReSS and ADReSSo datasets show that LAPE achieves state‑of‑the‑art performance in detecting Alzheimer’s disease from speech.
arXiv:2605.29859v2 Announce Type: replace-cross Abstract: Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of...
The paper introduces TextPro‑SLM, a speech large language model that reduces the modality gap by making spoken input resemble a prosody‑aware text LLM. It combines WhisperPro, a unified speech encoder that outputs synchronized text tokens and prosody embeddings, with an LLM backbone that retains the semantic power of the original text LLM while learning paralinguistic cues. Experiments demonstrate that TextPro‑SLM achieves the lowest modality gap among leading SLMs at both 3B and 7B scales, and performs strongly on paralinguistic understanding tasks using only about 1,000 hours of audio for training.
Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instability, evaluation confounding (up to 60% of reported WER attributable to style mismatch), and unreliable word-level timing.
OpenPA is a new automatic pronunciation assessment framework that eliminates the need for forced alignment by using Whisper’s cross‑attention to predict word‑ and utterance‑level scores. It adapts to mixed transcripts through mixed‑transcript adaptation and adaptive substitution weighting, enabling a single model to handle both closed‑ and open‑response settings. Trained only on speechocean762, OpenPA outperforms other systems on in‑domain closed and simulated open‑response tests, retains strong zero‑shot performance on MultiPA, and shows promise in oral‑cancer speech evaluation.