Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting

• URL: http://arxiv.org/abs/2505.16735v2
• Date: Fri, 23 May 2025 02:53:38 GMT
• Title: Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting
• Authors: Youngmoon Jung, Yong-Hyeok Lee, Myunghun Jung, Jaeyoung Roh, Chang Woo Han, Hoon-Young Cho,
• Abstract summary: For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level.<n>We optimize acoustic and text encoders using deep metric learning (DML), enabling direct comparison of multi-modal embeddings in a shared embedding space.<n>We propose Modality Adversarial Learning (MAL), which reduces the domain gap in heterogeneous modality representations.
• Score: 8.401528952094413
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For text enrollment-based open-vocabulary keyword spotting (KWS), acoustic and text embeddings are typically compared at either the phoneme or utterance level. To facilitate this, we optimize acoustic and text encoders using deep metric learning (DML), enabling direct comparison of multi-modal embeddings in a shared embedding space. However, the inherent heterogeneity between audio and text modalities presents a significant challenge. To address this, we propose Modality Adversarial Learning (MAL), which reduces the domain gap in heterogeneous modality representations. Specifically, we train a modality classifier adversarially to encourage both encoders to generate modality-invariant embeddings. Additionally, we apply DML to achieve phoneme-level alignment between audio and text, and conduct extensive comparisons across various DML objectives. Experiments on the Wall Street Journal (WSJ) and LibriPhrase datasets demonstrate the effectiveness of the proposed approach.

Related papers

• Implicit Counterfactual Learning for Audio-Visual Segmentation [50.69377287012591]
  We propose the implicit counterfactual framework (ICF) to achieve unbiased cross-modal understanding.<n>Due to the lack of semantics, heterogeneous representations may lead to erroneous matches.<n>We introduce the multi-granularity implicit text (MIT) involving video-, segment- and frame-level as the bridge to establish the modality-shared space.
  arXiv  Detail & Related papers  (2025-07-28T11:46:35Z)
• TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models [123.17643568298116]
  We present TAViS, a novel framework that textbfcouples the knowledge of multimodal foundation models for cross-modal alignment.<n> effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision.<n>Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.
  arXiv  Detail & Related papers  (2025-06-13T03:19:47Z)
• ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs [11.696352577108211]
  This work introduces ALAS (Automatic Latent Alignment Score), a metric that evaluates alignment by measuring correlations between audio and text representations across transformer layers.<n> Experiments on Spoken Question Answering and Emotion Recognition show that ALAS captures meaningful patterns across tasks and layers.
  arXiv  Detail & Related papers  (2025-05-26T13:02:44Z)
• Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation [20.415410280412697]
  We propose an Adaptive Inner Speech-Text Alignment (AI-STA) method to bridge the modality gap by explicitly aligning speech and text representations at selected layers within large language models (LLMs)<n> Experimental results on speech translation tasks demonstrate that AI-STA significantly improves the translation performance of large speech-text models (LSMs), outperforming previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-03-13T09:54:35Z)
• SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation [10.828717295018123]
  We propose a unified embedding framework that eliminates the need for intermediate text representations.<n>Our model reduces pipeline latency by 50% while achieving higher retrieval accuracy compared to traditional two-stage methods.
  arXiv  Detail & Related papers  (2025-01-26T15:04:02Z)
• Mind the Gap: A Generalized Approach for Cross-Modal Embedding Alignment [0.0]
  Retrieval-Augmented Generation (RAG) systems retrieve context across different text modalities due to semantic gaps. We introduce a generalized projection-based method, inspired by adapter modules in transfer learning, that efficiently bridges these gaps. Our approach emphasizes speed, accuracy, and data efficiency, requiring minimal resources for training and inference.
  arXiv  Detail & Related papers  (2024-10-30T20:28:10Z)
• Label-anticipated Event Disentanglement for Audio-Visual Video Parsing [61.08434062821899]
  We introduce a new decoding paradigm, underlinelabel sunderlineemunderlineantic-based underlineprojection (LEAP) LEAP works by iteratively projecting encoded latent features of audio/visual segments onto semantically independent label embeddings. To facilitate the LEAP paradigm, we propose a semantic-aware optimization strategy, which includes a novel audio-visual semantic similarity loss function.
  arXiv  Detail & Related papers  (2024-07-11T01:57:08Z)
• Text-Video Retrieval with Global-Local Semantic Consistent Learning [122.15339128463715]
  We propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL) GLSCL capitalizes on latent shared semantics across modalities for text-video retrieval. Our method achieves comparable performance with SOTA as well as being nearly 220 times faster in terms of computational cost.
  arXiv  Detail & Related papers  (2024-05-21T11:59:36Z)
• Learning Speech Representation From Contrastive Token-Acoustic Pretraining [57.08426714676043]
  We propose "Contrastive Token-Acoustic Pretraining (CTAP)", which uses two encoders to bring phoneme and speech into a joint multimodal space. The proposed CTAP model is trained on 210k speech and phoneme pairs, achieving minimally-supervised TTS, VC, and ASR.
  arXiv  Detail & Related papers  (2023-09-01T12:35:43Z)
• Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting [23.627625026135505]
  We propose a novel end-to-end user-defined keyword spotting method. Our method compares input queries with an enrolled text keyword sequence. We introduce the LibriPhrase dataset for efficiently training keyword spotting models.
  arXiv  Detail & Related papers  (2022-06-30T16:40:31Z)
• Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text [69.55642178336953]
  We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. We show that our approach is invariant to the variety of annotation styles as well as to the different languages of this collection.
  arXiv  Detail & Related papers  (2020-03-27T07:37:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.