paper-with-me

홈 › Papers

Recycle Your Wav2Vec2 Codebook: A Speech Perceiver for Keyword Spotting

2022-10-01 · COLING 2022 10 · Guillermo Cámbara, Jordi Luque, Mireia Farrús

Speech information in a pretrained wav2vec2.0 model is usually leveraged through its encoder, which has at least 95M parameters, being not so suitable for small footprint Keyword Spotting. In this work, we show an efficient way of profiting from wav2vec2.0’s linguistic knowledge, by recycling the phonetic information encoded in its latent codebook, which has been typically thrown away after pretraining. We do so by transferring the codebook as weights for the latent bottleneck of a Keyword Spotting Perceiver, thus initializing such model with phonetic embeddings already. The Perceiver design relies on cross-attention between these embeddings and input data to generate better representations. Our method delivers accuracy gains compared to random initialization, at no latency costs. Plus, we show that the phonetic embeddings can easily be downsampled with k-means clustering, speeding up inference in 3.5 times at only slight accuracy penalties.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword SpottingSmall-Footprint Keyword Spotting

Similar Papers 제목 키워드 기반

Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices

2025-08-06 · Yael Segal-Feldman, Ann R. Bradlow, Matthew Goldrick, Joseph Keshet arxiv

Open-vocabulary keyword spotting (KWS) refers to the task of detecting words or terms within speech recordings, regardless of whether they were included in the training data. This paper introduces an open-vocabulary keyw…

Keyword Spotting

Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers

2021-07-28 · Piper Wolters, Logan Sizemore, Chris Daw, Brian Hutchinson 외

Many applications involve detecting and localizing specific sound events within long, untrimmed documents, including keyword spotting, medical observation, and bioacoustic monitoring for conservation. Deep learning techn…

Event DetectionKeyword SpottingRegion ProposalSound Event Detection

On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation

2023-07-06 · Gene-Ping Yang, Yue Gu, Qingming Tang, Dongsu Du 외

Large self-supervised models are effective feature extractors, but their application is challenging under on-device budget constraints and biased dataset collection, especially in keyword spotting. To address this, we pr…

Keyword SpottingKnowledge DistillationRepresentation LearningSpeech Representation Learning

MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models

2026-06-04 · Aofei Chang, Le Huang, Alex James Boyd, Parminder Bhatia 외 arxiv

Medical large vision-language models (Med-LVLMs) have recently achieved remarkable progress in vision-language comprehension and medical image segmentation. However, existing models still struggle to unify these two capa…

Medical Image Segmentation

Efficient Speech Translation with Dynamic Latent Perceivers

2022-10-28 · Ioannis Tsiamas, Gerard I. Gállego, José A. R. Fonollosa, Marta R. Costa-jussà

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due…

Speech-to-TextSpeech-to-Text TranslationTranslation