arXiv AI September 1, 2026 By Gaopeng Xu, Chengfei Li, Xianliang Wang, Lin Zhu, Juan Wei, Wenpeng Li, Jianwei Niu, Jie Gao

PromptKWS: A Novel Prompt-Guided Open-Vocabulary Keyword Spotting Framework

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 11

Massive Open-Vocabulary Keyword Spotting

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.

By Leonor Barreiros, Raul Monteiro, Afonso Mendes, Gon\c{c}alo M. Correia

fine-tuning efficiency multimodal

Hugging Face Trending Papers

Jun 17

IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages

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.

llms multimodal benchmarks safety

arXiv Machine Learning

Jun 16

Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models

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.

By Hyebin Cho, Jaehyuk Jang, Changick Kim, Joon Son Chung

llms

arXiv Computation and Language

Oct 7

GIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword Spotting

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 (...

By Ming-Hsiang Hu, Kuan-Tang Huang, Hung-Shin Lee, Berlin Chen

benchmarks

arXiv AI

Sep 24

Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations

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.

By Marcin Sowa\'nski, Kacper Leszczy\'nski, Kacper Krzywicki, Krzysztof Wodnicki

arXiv Computation and Language

Sep 15

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

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...

By Warit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani, Sittipong Sripaisarnmongkol, Kunat Pipatanakul

llms agents multimodal benchmarks