aiqbench analysis
MERaLiON-GR demonstrates that parameter-efficient fine-tuning with LoRA can effectively adapt a large speech encoder for specialized paralinguistic tasks like gender recognition across diverse Southeast Asian languages. The model outperforms existing state-of-the-art systems and Audio LLMs, highlighting the continued relevance of dedicated architectures over general-purpose foundation models in specific acoustic domains.
MERaLiON-GR: Speech Gender Recognition Model for English and SEA Languages
arXiv:2608.04433v1 Announce Type: new 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.
Authors:Qiongqiong Wang, Ai Ti Aw, Nancy F. Chen, Ying Lay Chiu, Yang Ding, Yingxu He, Ridong Jiang, Zhuohan Liu, Yanfeng Lu, Yi Ma, Muhammad Huzaifah, Nabilah Binte Md Johan, Nattadaporn Lertcheva, Pham Minh Duc, Sailor Hardik Bhupendra, Siti Umairah Binte Mohammad Salleh, Shuo Sun, Tarun Kumar Vangani, Jeremy H. M. Wong, Jinyang Wu, Longyin Zhang
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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2608.04433 [cs.CL]
(or arXiv:2608.04433v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.04433 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 207 words
Related coverage
The Open ASR Leaderboard Adds Its First Global South Language
Hugging Face · Aug 28, 2026
SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia
arXiv · Sep 10, 2026
Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models
arXiv · Jun 11, 2026
Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models
arXiv · Sep 18, 2026