Blog(1)

• FSPEN: An Ultra-Lightweight Network for Real Time Speech Enhancement

  Speech enhancement or noise suppression aims at improving the quality and intelligibility of noisy speech. It is an important frontend module for voice call, automatic speech recognition (ASR), and hearing aids system.

Research Areas(0)

Publications(8)

• Open-Source Conversational AI with SpeechBrain 1.0

  AuthorTitouan Parcollet, Shucong Zhang

  PublishedJournal of Machine Learning Research

  Date2024-09-09

• An MVDR-Embedded U-Net Beamformer for Effective and Robust Multichannel Speech Enhancement

  AuthorChinghua Lee,Chouchang Yang,Yilin Shen,Hongxia Jin

  PublishedIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

  Date2024-04-14

• Leveraging Self-Supervised Speech Representations for Domain Adaptation in Speech Enhancement

  AuthorChinghua Lee,Chouchang Yang,Rakshith Srinivasa,Yashas Malur Saidutta,Jaejin Cho,Yilin Shen,Hongxia Jin

  PublishedIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

  Date2024-04-14

View More

News(3)

• [Blog] Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds

  Recently, true wireless stereo (TWS) earbuds have been successfully popularized along with mobile phones, thereby increasing convenience for many users. In line with this, companies developing earbuds have introduced a variety of functions to maximize user experience.

• [Blog] FSPEN: An Ultra-Lightweight Network for Real Time Speech Enhancement

  Speech enhancement or noise suppression aims at improving the quality and intelligibility of noisy speech. It is an important frontend module for voice call, automatic speech recognition (ASR), and hearing aids system.

• [Blog] [INTERSPEECH 2022 Series #5] Prototypical Speaker-Interference Loss for Target Voice Separation Using Non-Parallel Audio Samples

  Deep learning based audio signal processing is increasingly becoming popular for solving the cocktail party problem [1-5]. A noisy signal, which is mixed by a clean and noise signal, is used as a pair with the clean signal for training a speech enhancement or source separation model [6-7].

Others(0)