Home > Models & research

Models & research

Pioneering the future

Our team is pushing the boundaries of speech and language technology, driving innovation through purposeful, strategic projects.
Phase 1
AudioLLM V1DEC 2024
  • Transcription
  • Translation
  • Question-Answering
  • Summarisation
  • Supports English, Mandarin and Singlish
Phase 2
AudioLLM v2MAY 2025
  • Code-Switching Capabilities
  • Language-Mixing
  • Emotion and Paralinguistic Understanding
  • Supports English, Mandarin, Malay, Tamil, Singlish, Thai, Bahasa Indonesian and Vietnamese

Research library

  • /qws/slot/u50480/model-n-research/research-library-5.png
    Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation
    19 May 2025
    View research
  • /qws/slot/u50480/model-n-research/research-library-1.png
    AdaCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Chain-of-Thought
    27 Jan 2025
    View research
  • /qws/slot/u50480/model-n-research/research-library-2.png
    Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models
    2 Jan 2025
    View research
  • /qws/slot/u50480/model-n-research/research-library-6.png
    MERaLiON-SpeechEncoder: Towards a SpeechFoundation Model for Singapore and Beyond
    20 Dec 2024
    View research
  • /qws/slot/u50480/model-n-research/research-library-3.png
    MERaLiON-AudioLLM: Technical Report

    13 Dec 2024
    View research
  • /qws/slot/u50480/model-n-research/research-library-4.png
    MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders
    10 Sep 2024
    View research
  • /qws/slot/u50480/model-n-research/research-library-5.png
    AudioBench: A Universal Benchmark for Audio Large Language Models
    23 Jan 2024
    View research
  • /qws/slot/u50480/model-n-research/research-library-6.png
    SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
    9 Sep 2023
    View research