Blog(29)

• [INTERSPEECH 2025 Series #9] Fairness in Dysarthric Speech Synthesis: Understanding Intrinsic Bias in Dysarthric Speech Cloning using F5-TTS

  Voice cloning, especially zero-shot speech synthesis, has become one of the most exciting frontiers in speech technology.

• A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization

  Research in Automatic Speech Recognition (ASR) continues to show that larger models yield better results. But while state-of-the-art networks continue to grow with billions of parameters, the difficulty of deploying these models on device also increases.

• [INTERSPEECH 2025 Series #1] Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts

  Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts. We apply a efficient modular approach for STT.

View More

Research Areas(0)

Publications(40)

• Linear-Complexity Self-Supervised Learning for Speech Processing

  AuthorShucong Zhang, Titouan Parcollet, Rogier van Dalen, Sourav Bhattacharya

  PublishedAnnual Conference of the International Speech Communication Association (INTERSPEECH)

  Date2024-09-02

• 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

• Exploring compressibility of transformer based text-to-music (TTM) models

  AuthorPablo Peso Parada, Md Asif Jalal, Jisi Zhang, Karthikeyan Saravanan

  PublishedAnnual Conference of the International Speech Communication Association (INTERSPEECH)

  Date2024-09-01

View More

News(9)

• Samsung R&D Institute Poland Engineers Shine at INTERSPEECH 2025 Challenges and Conference

  The AI Solutions team at Samsung R&D Institute Poland (SRPOL) achieved outstanding results at INTERSPEECH 2025, securing 1st place in the Mice Autism Detection via Ultrasound Vocalisation (MADUV) Challenge, 2nd place in the Speech Emotion Recognition in Naturalistic Conditions Challenge, and having five papers accepted for presentation at the conference.

• Samsung Research at SpeechBrain 2023 Online Summit - ISCA 2023 Interspeech Satellite Event

  The Samsung AI Center – Cambridge is co-organizing alongside other academic and industrial partners an official ISCA 2023 Interspeech Satellite Event taking the form of a one-day long “Online SpeechBrain Summit” on August 28th.

• [Blog] [INTERSPEECH 2022 Series #6] Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition

  Automatic Speech Recognition (ASR) systems on smart devices have traditionally relied on server based models. This involves sending audio data to the server and receiving text hypothesis once the server model completes decoding.

View More

Others(0)