Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech

• URL: http://arxiv.org/abs/2603.07513v1
• Date: Sun, 08 Mar 2026 07:34:15 GMT
• Title: Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
• Abstract summary: Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology.<n>We present the first dedicated open-source neural TTS system designed for Kashmiri.
• Score: 2.00542420408131
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive human-computer interaction for native speakers. In this work, we present the first dedicated open-source neural TTS system designed for Kashmiri. We show that zero-shot multilingual baselines trained for Indic languages fail to produce intelligible speech, achieving a Mean Opinion Score (MOS) of only 1.86, largely due to inadequate modeling of Perso-Arabic diacritics and language-specific phonotactics. To address these limitations, we propose Bolbosh, a supervised cross-lingual adaptation strategy based on Optimal Transport Conditional Flow Matching (OT-CFM) within the Matcha-TTS framework. This enables stable alignment under limited paired data. We further introduce a three-stage acoustic enhancement pipeline consisting of dereverberation, silence trimming, and loudness normalization to unify heterogeneous speech sources and stabilize alignment learning. The model vocabulary is expanded to explicitly encode Kashmiri graphemes, preserving fine-grained vowel distinctions. Our system achieves a MOS of 3.63 and a Mel-Cepstral Distortion (MCD) of 3.73, substantially outperforming multilingual baselines and establishing a new benchmark for Kashmiri speech synthesis. Our results demonstrate that script-aware and supervised flow-based adaptation are critical for low-resource TTS in diacritic-sensitive languages. Code and data are available at: https://github.com/gaash-lab/Bolbosh.

Related papers

• PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects [29.32197370490759]
  PolySpeech-100 is a massive-scale benchmark designed to assess native-level' speech comprehension across 110 linguistic variants.<n>We employ a novel hybrid construction pipeline that augments gold-standard human recordings with instruction-driven synthetic speech.
  arXiv  Detail & Related papers  (2026-05-31T05:13:32Z)
• ks-lit-3m: A 3.1 million word kashmiri text dataset for large language model pretraining [0.0]
  This paper introduces KS-LIT-3M, a curated corpus of 3.1 million words (16.4 million characters) specifically designed for pretraining language models on Kashmiri.<n>The dataset is released under the CC-BY-4.0 license to facilitate research in Kashmiri natural language processing.
  arXiv  Detail & Related papers  (2026-01-03T06:43:26Z)
• Context-Aware Whisper for Arabic ASR Under Linguistic Varieties [27.039946482465268]
  We propose context-aware prompting strategies to adapt OpenAI's Whisper for Arabic speech recognition without retraining.<n>We introduce techniques such as prompt reordering, speaker-aware prefix synthesis, and modality-specific retrieval.<n>Our approach reduces WER by up to 22.3% on Modern Standard Arabic and 9.2% on dialectal speech.
  arXiv  Detail & Related papers  (2025-11-24T05:16:04Z)
• ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction [88.41471266579333]
  We propose ELEGANCE, a novel framework that incorporates linguistic knowledge from large language models (LLMs) into AV-TSE models.<n> Comprehensive experiments with RoBERTa, Qwen3-0.6B, and Qwen3-4B on two AV-TSE backbones show significant improvements.
  arXiv  Detail & Related papers  (2025-11-09T08:50:11Z)
• Kinship in Speech: Leveraging Linguistic Relatedness for Zero-Shot TTS in Indian Languages [6.74683227658822]
  India has 1369 languages, with 22 official using 13 scripts.<n>Our work focuses on zero-shot synthesis, particularly for languages whose scripts and phonotactics come from different families.<n>Intelligible and natural speech was generated for Sanskrit, Maharashtrian and Canara Konkani, Maithili and Kurukh.
  arXiv  Detail & Related papers  (2025-06-04T12:22:24Z)
• CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training [70.31925012315064]
  We present CosyVoice 3, an improved model designed for zero-shot multilingual speech synthesis in the wild.<n>Key features of CosyVoice 3 include a novel speech tokenizer to improve prosody naturalness.<n>Data is expanded from ten thousand hours to one million hours, encompassing 9 languages and 18 Chinese dialects.
  arXiv  Detail & Related papers  (2025-05-23T07:55:21Z)
• CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving [61.73180469072787]
  We focus on the problem of spoken translation (ST) of code-switched speech in Indian languages to English text. We present a new end-to-end model architecture COSTA that scaffolds on pretrained automatic speech recognition (ASR) and machine translation (MT) modules. COSTA significantly outperforms many competitive cascaded and end-to-end multimodal baselines by up to 3.5 BLEU points.
  arXiv  Detail & Related papers  (2024-06-16T16:10:51Z)
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias [71.94109664001952]
  Mega-TTS is a novel zero-shot TTS system that is trained with large-scale wild data. We show that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS speech editing, and cross-lingual TTS tasks.
  arXiv  Detail & Related papers  (2023-06-06T08:54:49Z)
• SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech [0.3277163122167433]
  SANE-TTS is a stable and natural end-to-end multilingual TTS model. We introduce speaker regularization loss that improves speech naturalness during cross-lingual synthesis. Our model generates speeches with moderate rhythm regardless of source speaker in cross-lingual synthesis.
  arXiv  Detail & Related papers  (2022-06-24T07:53:05Z)
• Cross-lingual Low Resource Speaker Adaptation Using Phonological Features [2.8080708404213373]
  We train a language-agnostic multispeaker model conditioned on a set of phonologically derived features common across different languages. With as few as 32 and 8 utterances of target speaker data, we obtain high speaker similarity scores and naturalness comparable to the corresponding literature.
  arXiv  Detail & Related papers  (2021-11-17T12:33:42Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition [148.43282526983637]
  We develop LRSpeech, a TTS and ASR system for languages with low data cost. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.
  arXiv  Detail & Related papers  (2020-08-09T08:16:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.