{"ID":2859504,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.06188","arxiv_id":"2510.06188","title":"BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects","abstract":"Real-time speech assistants are becoming increasingly popular for ensuring improved accessibility to information. Bengali, being a low-resource language with a high regional dialectal diversity, has seen limited progress in developing such systems. Existing systems are not optimized for real-time use and focus only on standard Bengali. In this work, we present BanglaTalk, the first real-time speech assistance system for Bengali regional dialects. BanglaTalk follows the client-server architecture and uses the Real-time Transport Protocol (RTP) to ensure low-latency communication. To address dialectal variation, we introduce a dialect-aware ASR system, BRDialect, developed by fine-tuning the IndicWav2Vec model in ten Bengali regional dialects. It outperforms the baseline ASR models by 12.41-33.98% on the RegSpeech12 dataset. Furthermore, BanglaTalk can operate at a low bandwidth of 24 kbps while maintaining an average end-to-end delay of 4.9 seconds. Low bandwidth usage and minimal end-to-end delay make the system both cost-effective and interactive for real-time use cases, enabling inclusive and accessible speech technology for the diverse community of Bengali speakers. Code is available in https://github.com/Jak57/BanglaTalk","short_abstract":"Real-time speech assistants are becoming increasingly popular for ensuring improved accessibility to information. Bengali, being a low-resource language with a high regional dialectal diversity, has seen limited progress in developing such systems. Existing systems are not optimized for real-time use and focus only on...","url_abs":"https://arxiv.org/abs/2510.06188","url_pdf":"https://arxiv.org/pdf/2510.06188v2","authors":"[\"Jakir Hasan\",\"Shubhashis Roy Dipta\"]","published":"2025-10-07T17:47:39Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":608646,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2859504,"paper_url":"https://arxiv.org/abs/2510.06188","paper_title":"BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects","repo_url":"https://github.com/Jak57/BanglaTalk","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}