Blog(7)

• Robust Speaker Personalisation Using Generalized Low-Rank Adaptation for Automatic Speech Recognition

  Automatic Speech Recognition (ASR) system is a critical element in many applications, including voice assistants, transcription services, and speech-to-text technology.

• Consistency Based Unsupervised ASR Personalisation

  Nowadays, voice assistants have been widely used by users to control smart phones. An automatic speech recognition (ASR) model plays a crucial role in the voice assistant system to recognise the user voice command, which is subsequently used for downstream tasks such as spoken language understanding and speech translation.

• pMCT - Patched Multi-Condition Training

  The clashing of pans and pots as you cook and ask your voice assistant what you can use to replace eggs in the recipe. The excited, overlapping conversations as you ask which of Henry the VIIIs wives survived, trying to settle a bet.

View More

Research Areas(0)

Publications(31)

• Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition

  AuthorTitouan Parcollet, Rogier van Dalen, Shucong Zhang, Sourav Bhattacharya

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

  Date2025-04-07

• SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding

  AuthorTitouan Parcollet, Rogier van Dalen, Shucong Zhang, Sourav Bhattacharya

  PublishedAnnual Conference of the International Speech Communication Association (INTERSPEECH)

  Date2024-09-02

• Improved Small-Footprint ASR-Based Solution for Open Vocabulary Keyword Spotting

  AuthorMikolaj Pudo, Mateusz Wosik, Artur Janicki

  PublishedIEEE Access

  Date2024-07-01

View More

News(12)

• [Blog] A Unified Approach to Multilingual Automatic Speech Recognition with Improved Language Identification for Indic Languages

  Multilingual Automatic Speech Recognition (ASR) presents several challenges, especially when multiple languages are being spoken in the same audio.

• [Blog] Speaker Personalization for Automatic Speech Recognition using Weight-Decomposed Low-Rank Adaptation

  Personalizing automated speech recognition (ASR) for voice assistant systems is often considered the holy grail, requiring meticulous attention to detail in model optimization.

• [Blog] Robust Speaker Personalisation Using Generalized Low-Rank Adaptation for Automatic Speech Recognition

  Automatic Speech Recognition (ASR) system is a critical element in many applications, including voice assistants, transcription services, and speech-to-text technology.

View More

Others(0)