MERaLiON-GR: Speech Gender Recognition Model for English and SEA Languages

2026/08/05 by Qiongqiong Wang, Ai Ti Aw, Nancy F. Chen +18
Computer Science · #cs.CL #cs.AI

paper · pdf

arxiv created 2026/08/05 · arxiv updated 2026/08/06

Abstract

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.

Citations

• Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data
• Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models
• THAI Speech Emotion Recognition (THAI-SER) corpus
• Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits
• Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation
• Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models
• A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
• FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
• wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
• ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
• Common Voice: A Massively-Multilingual Speech Corpus
• Class-Balanced Loss Based on Effective Number of Samples
• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset