- Code for the paper 'MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting', Interspeech 2024 accepted
- Arxiv: https://arxiv.org/pdf/2406.07310
- The code will be released in this month, I'm busy with my masters thesis
- LibriPhrase:
- WenetPhrase:
- Speech Command:
![](https://private-user-images.githubusercontent.com/98506724/339391291-a893c8b5-7104-4044-87ed-85d418e33f0b.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTk3NzY3ODEsIm5iZiI6MTcxOTc3NjQ4MSwicGF0aCI6Ii85ODUwNjcyNC8zMzkzOTEyOTEtYTg5M2M4YjUtNzEwNC00MDQ0LTg3ZWQtODVkNDE4ZTMzZjBiLnBuZz9YLUFtei1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxTQTUzUFFLNFpBJTJGMjAyNDA2MzAlMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQwNjMwVDE5NDEyMVomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlPWExNjY1M2MzZDc1MDU0ZmZjMzM3ZDkyMzMwZTA5NTY3Njc5ZTM4ZDkwODUzYWZlM2Y2OWM0YzUzODc4ZWRhZTQmWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0JmFjdG9yX2lkPTAma2V5X2lkPTAmcmVwb19pZD0wIn0.LDMf0Q1LlTxUvSBYxFfKH8qYlZxCbuCW0m9-AOB8Faw)
![](https://private-user-images.githubusercontent.com/98506724/339392225-450d14f3-9621-44cb-8156-9f4e80b34ab9.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.I2Sh7OHSL7QTEn0fXr3Nmq8ggaaL7noxCOGq80-fzNo)
![](https://private-user-images.githubusercontent.com/98506724/339392330-5736d986-ddd0-4059-8897-2bcc47942f79.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.P6OzPOJ5DwmvkugQKvu7YqLkgu1ZxrUp7Rk2MIg5UQ8)
Note: I wrote about the wake word experiment for my master thesis, which was deleted from the Interspeech manuscript due to space limit.