Metraipolis › archive › dc_3d01e9519469

TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems — arXiv:2608.21343

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21343
License (as archived)
CC0-1.0
Archived
2026-10-18T10:18:43.543Z
SHA-256 of the archived text
e48c271480d55c80cff95a94ee4725d7db18629f4669554386c1efe0db3040d3
Stable URL of this page
https://metraipolis.com/documento/dc_3d01e9519469

How to cite

TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems — arXiv:2608.21343 — arXiv (en), https://arxiv.org/abs/2608.21343 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d01e9519469 (Metraipolis archive dc_3d01e9519469, sha256 e48c271480d55c80cff95a94ee4725d7db18629f4669554386c1efe0db3040d3)
BibTeX
@misc{dc3d01e9519469,
  title = {TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems — arXiv:2608.21343},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21343},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d01e9519469; sha256 e48c271480d55c80cff95a94ee4725d7db18629f4669554386c1efe0db3040d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21343. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contextualization is essential for production automatic speech recognition (ASR) systems, where user-provided phrases must be recognized accurately under strict latency constraints. Although many context-biasing methods improve recognition accuracy, they often do not address the practical requirements of modern production ASR systems: streaming inference, efficient batched decoding, user-specific context lists, and low runtime overhead. We propose TurboBias 2.0, a production-oriented framework for efficient phrase boosting in Transducer-based ASR systems. The framework extends GPU-accelerated TurboBias with a case-insensitive boosting graph and per-stream batched decoding, allowing each utterance in a batch to use an independent context-biasing configuration. This enables personalized context biasing for multiple simultaneous users without sharing or mixing their context lists. The proposed framework supports both offline and streaming inference and can be used with greedy and beam-search decoding. Experiments show that TurboBias 2.0 improves contextual phrase recognition while preserving low latency and high throughput.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CL).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2608.21343 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:17:37.622Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).