PromptKWS is a new prompt‑guided keyword spotting framework that enhances open‑vocabulary KWS accuracy. It introduces the Prompt Phrases Prediction Network (PPN), an encoder‑decoder that extracts keyword prompt embeddings, which are then integrated into the KWS encoder via a Prompt‑acoustic Multi‑head Cross‑attention module. Experiments show that PromptKWS raises the wake‑up rate by more than 10% and improves overall accuracy by over 15% in noisy, pronunciation‑variant real‑world settings.
arXiv:2606. 11279v1 Announce Type: cross Abstract: Automatic speech recognition systems have been shown to under-perform when it comes to transcribing words rarely seen in the training data, namely specialized terminology.
AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear whether these models genuinely utilise such context or rely on parametric knowledge learned during pretraining.
arXiv:2606. 15751v1 Announce Type: cross Abstract: Audio-Language Models (ALMs) have shown remarkable success in zero-shot audio classification by aligning audio waveforms with text.
arXiv:2610.07046v1 Announce Type: cross Abstract: Visual speech promises noise-robust keyword spotting, yet a visual stream is not necessarily used. On a tri-modal query-by-example keyword spotting (...
The paper presents a new wake‑up system for voice assistants that goes beyond simple keyword spotting by adding contextual trigger detection. After the wake word is heard, the system reasons to differentiate between actual user commands and unrelated speech, enabling more efficient and context‑aware interactions. A data‑generation architecture is introduced that creates a 62.3‑hour corpus of controllable multi‑speaker conversations, including direct invocations, contextual follow‑ups, and non‑addressed speech, and experimental results confirm the approach’s effectiveness across varied synthetic scenarios.
arXiv:2609.14991v1 Announce Type: new Abstract: Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling ou...
Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out low-latency uses such as live captioning and vo...
BanglaTurn is a new corpus of 35,374 Bangla podcast speech samples, each 3 to 15 seconds long, labeled for end‑of‑turn detection through speaker diarization, an LLM pass, and human verification. A Whisper‑based model with task‑specific classification heads achieves 84.33 % accuracy on a balanced test set, outperforming the Smart‑Turn v3 baseline (69.28 %) and reducing the false‑negative rate from 51.57 % to 7.55 %, though with a higher false‑positive rate. The study also details the contributions of encoder‑layer fine‑tuning, multi‑scale pooling, INT8 quantization, and reports inference latency of 165–191 ms on CPU.
SPAR-K is a scheduled periodic alternating early‑exit framework for interleaved spoken language models that reduces decoding depth for speech tokens while maintaining quality. It lets most speech positions exit at a fixed intermediate layer and inserts periodic full‑depth refresh steps to counter distribution shift. Experiments on Step‑Audio‑2‑mini and GLM‑4‑Voice show up to 11 % depth reduction with less than 0.82 % drop in question‑answering accuracy and negligible impact on MOS and WER.
arXiv:2606. 06837v1 Announce Type: cross Abstract: Scripted vs spontaneous speech detection is appealing for interview guardrails, but benchmark performance can be inflated by shortcuts tied to corpus identity, channel conditions, and recording artifacts rather than speaking style itself.
arXiv:2609.21183v1 Announce Type: cross Abstract: Audio large language models (AudioLLMs) operate reactively, responding only when queried. We introduce proactive audio assistance, where an AudioLLM...
SEA-SpeechBench is a large‑scale multitask benchmark for speech understanding in 11 Southeast Asian languages, comprising 97,194 samples across 99 evaluation sets and 597 hours of curated audio. It covers nine tasks in three categories—speech processing, paralinguistic analysis, and a novel temporal understanding dimension—using multilingual prompting in both native SEA languages and English. Evaluation of current models shows significant performance gaps, especially in temporal understanding, emotion recognition, and speech translation, with low‑resource languages lagging behind English by up to 41 percentage points.