Blog(1)

• [INTERSPEECH 2025 Series #3] Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting

  Text-enrolled KWS with phoneme-level deep metric learning and adversarial training. We align acoustic and text embeddings across modalities and achieve SOTA on WSJ & LibriPhrase.

Research Areas(0)

Publications(4)

• Joint Embedding Learning and Latent Subspace Probing for Cross-Domain Few-Shot Keyword Spotting

  AuthorMete Ozay

  PublishedInternational Conference on Acoustics, Speech and Signal Processing (ICASSP)

  Date2024-03-18

• Robust Keyword Spotting for Noisy Environments by Leveraging Speech Enhancement and Speech Presence Probability

  AuthorChouchang Yang,Yashas Malur Saidutta,Rakshith Srinivasa,Chinghua Lee,Yilin Shen,Hongxia Jin

  PublishedAnnual Conference of the International Speech Communication Association (INTERSPEECH)

  Date2023-08-21

• MOCKS 1.0: Multilingual Open Custom Keyword Spotting Testset

  AuthorMikolaj Pudo, Mateusz Wosik, Adam Cieslak, Justyna Krzywdziak, Bozena Lukasiak, Artur Janicki

  PublishedAnnual Conference of the International Speech Communication Association (INTERSPEECH)

  Date2023-08-20

View More

News(5)

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

  Text-enrolled KWS with phoneme-level deep metric learning and adversarial training. We align acoustic and text embeddings across modalities and achieve SOTA on WSJ & LibriPhrase.

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

  Text-enrolled KWS with phoneme-level deep metric learning and adversarial training. We align acoustic and text embeddings across modalities and achieve SOTA on WSJ & LibriPhrase.

• [Blog] Text-Aware Adapter for Few-Shot Keyword Spotting

  Keyword spotting (KWS) is a technique for detecting pre-defined keywords in audio streams.

View More

Others(0)