Search papers, labs, and topics across Lattice.
MERaLiON-GR is a speech gender recognition model that utilizes a fine-tuned MERaLiON-SpeechEncoder-2 and employs Low-Rank Adaptation (LoRA) for efficient parameter tuning. It integrates a multi-scale ECAPA-TDNN downstream network with attention pooling, achieving superior performance in gender classification across multiple languages, including English and various Southeast Asian languages. The model outperforms the state-of-the-art Vox-Profile and a large Audio-LLM in both full-utterance and segment-level evaluations, highlighting its effectiveness in paralinguistic tasks and cross-lingual generalization.
MERaLiON-GR outperforms existing models in gender recognition across multiple Southeast Asian languages, showcasing the power of specialized speech models.
We present MERaLiON-GR, a speech gender recognition system that performs binary classification (female / male) on English and Southeast Asian (SEA) languages. The model finetunes MERaLiON-SpeechEncoder-2, a large conformer based transformer pre-trained on a broad speech corpus, and applies parameter efficient fine-tuning via Low-Rank Adaptation (LoRA) to adapt the encoder to the gender recognition task, and appends a multi-scale ECAPA-TDNN down stream network with attention pooling and a lightweight linear classifier. Extensive evaluations across multilingual Singaporean and Southeast Asian languages (English, Chinese, Malay, Tamil, Thai, Vietnamese, Indonesian, and Khmer) show that MERaLiON-GR consistently surpasses the state-of-the-art gender recognition model Vox-Profile and a large Audio-LLM, in both full-utterance and segment level evaluation modes. The results underscore the value of dedicated speech models in achieving accurate paralinguistic understanding and strong cross-lingual generalization.
