{
  "id": 2451106,
  "title": "A modular offline multilingual speech-to-speech translation system with confidence-aware ASR routing and language-aware TTS",
  "url": "https://urgent.news/2026/08/21/a-modular-offline-multilingual-speech-to-speech-translation-system",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-21T23:40:25.000Z",
  "source": {
    "name": "Scientific Reports",
    "slug": "scientific-reports",
    "url": "https://www.nature.com/articles/s41598-026-67788-0"
  },
  "original_language": "en",
  "account": "Offline speech-to-speech translation offers privacy and connectivity benefits for constrained applications, but local deployment demands an optimal balance of recognition accuracy, language coverage, and latency. The authors introduce a modular, fully offline, turn-based system that integrates language identification, confidence-aware automatic speech recognition routing, multilingual machine translation, and language-aware speech synthesis. The system tested with Hindi, Telugu, Tamil, Bengali, French, German, Arabic, and Japanese as source/target languages, using FLEURS, FLORES-200, and CVSS benchmarks. A routing threshold of 0.70 resulted in 97.65% routing accuracy, significantly lowering recognition errors in four Indic languages compared to Whisper-only recognition. The study demonstrates that clean-versus-cascaded translation experiments show recognition error propagation in machine translation. End-to-end ASR-BLEU scores range from 31.4 to 39.2 across five CVSS-supported source-to-English directions, while eight-language speech-synthesis evaluation yields mean opinion scores between 3.55 and 4.12 and back-ASR WER ranging from 6.8 to 10.8%. The modular system's mean model-only CPU latency is 25.41 seconds, with translation and speech synthesis consuming the majority of processing time. The results illustrate the accuracy-precision-latency trade-offs in offline multilingual speech translation on local CPU execution.",
  "summary": "Scientific Reports, Published online: 22 August 2026; doi:10.1038/s41598-026-67788-0 A modular offline multilingual speech-to-speech translation system with confidence-aware ASR routing and language-aware TTS",
  "key_points": [
    "Modular offline system integrates language identification, routing, translation, and synthesis",
    "Routing threshold of 0.70 lowers recognition errors in Indic languages",
    "Mean model-only CPU latency of 25.41 seconds for offline multilingual speech translation"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}