The paper evaluates pseudo‑labeling to adapt pretrained ASR models (Whisper and Qwen3‑ASR) for noisy Broadcast Police Communication (BPC) from Baltimore and Chicago. It finds that internal confidence metrics cannot reliably separate high‑ and low‑quality pseudo‑labels, and proposes an external LLM‑as‑a‑judge filtering approach that more aggressively removes implausible transcripts, reducing WER. Additionally, a cross‑model pseudo‑labeling strategy is introduced, where one model is fine‑tuned with pseudo‑labels from the other, showing promise for future work.
arXiv:2601. 11670v3 Announce Type: replace-cross Abstract: Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance.
arXiv:2609.23462v1 Announce Type: cross Abstract: Non-verbal vocalizations (NVVs) carry important paralinguistic information but are often omitted by conventional automatic speech recognition (ASR) s...
The paper presents a data‑centric approach to improve automatic speech recognition for non‑verbal vocalizations (NVVs) in the ISCSLP NVVSpeech Challenge. It introduces cross‑dataset label harmonization and a two‑stage sampling schedule—first square‑root category sampling to address long‑tailed distributions, then uniform‑category fine‑tuning—to jointly transcribe lexical content and 16 NVV categories. The final system achieved an official score of 63.86, ranking fourth in Track 1.
arXiv:2608. 19936v1 Announce Type: cross Abstract: Public benchmarks are important measures of Automatic Speech Recognition (ASR) model capabilities.
The paper investigates how streaming emotion recognition models can be misled by their own prior predictions, a problem termed previous-belief contamination (PBC). Using a counterfactual diagnostic on CREMA-D-Stream, the authors show that feeding a model’s previous emotion label into its current prediction can drastically lower accuracy and flip many predictions, with the effect varying by label. To mitigate PBC, they propose EmoUpdate, a training‑free framework that isolates current audio perception from historical context through a prior‑blind firewall, a causal belief filter, and a decontamination operator, achieving significant gains across multiple SpeechLMs and benchmarks.
The paper introduces asymmetric classifier‑free guidance (CFG) for target‑speaker ASR using Whisper, where a speaker‑conditioned branch predicts the target transcript and a speaker‑unconditioned branch predicts serialized multi‑speaker transcripts. CFG modulates the influence of speaker conditioning during decoding via a single guidance scale, which is first set globally on development data and then refined per utterance by a lightweight encoder‑based predictor while keeping the recognition model fixed. The resulting system yields up to 21.8% relative WER reduction over a condition‑only baseline and 5.6% over standard conditional decoding under domain shifts.
arXiv:2606. 10912v1 Announce Type: cross Abstract: Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision.
arXiv:2608.29120v1 Announce Type: cross Abstract: Speech Language Models (SLMs) are increasingly deployed in multi-speaker environments, yet their ability to attribute speech to the correct speaker a...
arXiv:2606. 29031v1 Announce Type: cross Abstract: In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from modern text-to-speech (TTS) is an appealing alternative for training automatic speech recognition (ASR) without exposing sensitive customer recordings.
The paper introduces a Calibrated Reflection approach to improve confidence estimation in Large Language Models (LLMs). It combines structured reasoning with a distance‑aware calibration technique, featuring a Maximum Confidence Selection method, a reflection‑based prompting mechanism, and an ordinal‑aware calibration strategy. Experiments on datasets such as HelpSteer2, Llama T‑REx, and a proprietary conversational set show the method works for both conversational and fact‑based classification tasks.
The paper investigates whether audio large language models (Audio LLMs) can detect when their own transcriptions are unreliable. It finds that the models are poor at self-assessment and that existing methods offer limited detection. By leveraging audio-encoder representations, the authors develop a lightweight predictor that accurately flags unreliable transcriptions and can prompt user clarification without altering the underlying model.
arXiv:2606. 27698v1 Announce Type: cross Abstract: Automatic Speech Recognition systems are notoriously both sensitive to adversarial and benign perturbations.