Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing

• URL: http://arxiv.org/abs/2607.18934v1
• Date: Tue, 21 Jul 2026 10:19:17 GMT
• Title: Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
• Abstract summary: We show that models already encode both styles; the challenge is controlled activation.<n>Using coverage-aware decoder task tokens trained on parallel verbatim/intended transcript pairs, we raise German disfluency F1 from 10% to 79% zero-shot.<n>Full English-only fine-tuning surpasses all baselines in verbatim accuracy, disfluency detection, and intended-mode quality across both languages.
• Score: 8.921166277011347
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instability, evaluation confounding (up to 60% of reported WER attributable to style mismatch), and unreliable word-level timing. We show that models already encode both styles; the challenge is controlled activation. Using coverage-aware decoder task tokens trained on parallel verbatim/intended transcript pairs, we raise German disfluency F1 from 10% to 79% zero-shot, despite English-only training. Full English-only fine-tuning surpasses all baselines in verbatim accuracy, disfluency detection, and intended-mode quality across both languages. We further introduce supervised cross-attention fine-tuning that improves word-level timestamps on disfluent speech beyond forced-alignment baselines. Finally, we propose verbatimize, a new task enabling scalable creation and enrichment of speech corpora with high-quality canonical verbatim transcriptions.

Related papers

• Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs [32.94544776067079]
  ASR transcripts often contain disfluencies, such as fillers, repetitions, and false starts.<n>Most existing approaches rely on classical models that focus on identifying disfluent tokens for removal.<n>We propose a multilingual correction pipeline where a sequence tagger first marks disfluent tokens, and these signals guide instruction fine-tuning of an LLM to rewrite transcripts into fluent text.
  arXiv  Detail & Related papers  (2026-05-12T15:11:36Z)
• Simultaneous Speech-to-Speech Translation Without Aligned Data [52.467808474293605]
  Simultaneous speech translation requires translating source speech into a target language in real-time.<n>We propose Hibiki-Zero, which eliminates the need for word-level alignments entirely.<n>Hibiki-Zero achieves state-of-the-art performance in translation accuracy, latency, voice transfer, and naturalness across five X-to-English tasks.
  arXiv  Detail & Related papers  (2026-02-11T17:41:01Z)
• Smooth Operators: LLMs Translating Imperfect Hints into Disfluency-Rich Transcripts [5.439020425819001]
  Large language models (LLMs) are versatile learners capable of processing both lexical and non-lexical inputs.<n>We propose a novel approach to disfluencies as explicit tokens with timestamps, enabling the generation of fully annotated disfluency-rich transcripts.
  arXiv  Detail & Related papers  (2025-06-23T11:04:20Z)
• Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically [58.019484208091534]
  Cross-lingual alignment in pretrained language models (LMs) has enabled efficient transfer in text-based LMs.<n>It remains an open question whether findings and methods from text-based cross-lingual alignment apply to speech.
  arXiv  Detail & Related papers  (2025-05-26T07:21:20Z)
• BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection [8.303512060791736]
  Spoken term detection is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching.<n>We propose a novel approach that encodes speech into discrete, speaker-agnostic semantic tokens.<n>This facilitates fast retrieval using text-based search algorithms and effectively handles out-of-vocabulary terms.
  arXiv  Detail & Related papers  (2024-11-21T13:05:18Z)
• Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation [79.96416609433724]
  Zero-shot translation (ZST) aims to translate between unseen language pairs in training data. The common practice to guide the zero-shot language mapping during inference is to deliberately insert the source and target language IDs. Recent studies have shown that language IDs sometimes fail to navigate the ZST task, making them suffer from the off-target problem.
  arXiv  Detail & Related papers  (2023-09-28T17:02:36Z)
• Adversarial Training For Low-Resource Disfluency Correction [50.51901599433536]
  We propose an adversarially-trained sequence-tagging model for Disfluency Correction (DC) We show the benefit of our proposed technique, which crucially depends on synthetically generated disfluent data, by evaluating it for DC in three Indian languages. Our technique also performs well in removing stuttering disfluencies in ASR transcripts introduced by speech impairments.
  arXiv  Detail & Related papers  (2023-06-10T08:58:53Z)
• CTC-based Non-autoregressive Speech Translation [51.37920141751813]
  We investigate the potential of connectionist temporal classification for non-autoregressive speech translation. We develop a model consisting of two encoders that are guided by CTC to predict the source and target texts. Experiments on the MuST-C benchmarks show that our NAST model achieves an average BLEU score of 29.5 with a speed-up of 5.67$times$.
  arXiv  Detail & Related papers  (2023-05-27T03:54:09Z)
• Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation [37.48971774827332]
  We propose to generate ST tokens out-of-order while remembering how to re-order them later. We examine two variants of such operation sequences which enable generation of monotonic transcriptions and non-monotonic translations.
  arXiv  Detail & Related papers  (2022-11-11T02:29:28Z)
• Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation [71.35243644890537]
  End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space. We propose a novel Discrete Cross-Modal Alignment (DCMA) method that employs a shared discrete vocabulary space to accommodate and match both modalities of speech and text.
  arXiv  Detail & Related papers  (2022-10-18T03:06:47Z)
• SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training [33.02912456062474]
  We build a single encoder with the BERT objective on unlabeled text together with the w2v-BERT objective on unlabeled speech. We demonstrate that incorporating both speech and text data during pre-training can significantly improve downstream quality on CoVoST2 speech translation.
  arXiv  Detail & Related papers  (2021-10-20T00:59:36Z)

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.