No article text was recorded for this version.
ASR output normalization
Version 2 of 291 papers115 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Punctuation insertion for real-time spoken language translation
- Blog: Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery Models
- Blog: The University of Helsinki Submission to the IWSLT2020 Offline SpeechTranslation Task
- Blog: The University of Helsinki Submission to the IWSLT2020 Offline SpeechTranslation Task
- Blog: Open Source Toolkit for Speech to Text Translation
- Blog: MSR-FBK IWSLT 2013 SLT system description
- Blog: The TALP&I2r SMT systems for IWSLT 2008
- Blog: HiTZketan. Ahots-ahots itzulpen elebiduna ikasketa sakona erabiliz
- Blog: The KIT translation systems for IWSLT 2014
- Blog: A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation
- Blog: The IWSLT 2019 KIT Speech Translation System
- Blog: The KIT translation systems for IWSLT 2013
- Blog: Edinburgh SLT and MT system description for the IWSLT 2014 evaluation
- Blog: Simple and Effective Unsupervised Speech Translation
- Blog: KIT's IWSLT 2018 SLT Translation System
- Blog: Machine translation of multi-party meetings: segmentation and disfluency removal strategies
- Blog: Improve Speech Translation Through Text Rewrite
- Blog: The KIT translation systems for IWSLT 2015
- Blog: Just-in-time prepared captioning for live transmissions
- Blog: On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models
- Blog: English SLT and MT system description for the IWSLT 2013 evaluation
- Blog: ORCHID: A Chinese Debate Corpus for Target-Independent Stance Detection and Argumentative Dialogue Summarization
- Blog: Improved machine translation of speech-to-text outputs
- Blog: CS2W: A Chinese Spoken-to-Written Style Conversion Dataset with Multiple Conversion Types
- Blog: HiFiTTS-2: A Large-Scale High Bandwidth Speech Dataset
- Blog: tRuEcasIng
- Blog: EHU at TweetMT: Adapting MT Engines for Formal Tweets
- Blog: Multilingual Disfluency Removal using NMT
- Blog: Speech Translation with Style: AppTek’s Submissions to the IWSLT Subtitling and Formality Tracks in 2023
- Blog: Learning to Answer Visual Questions from Web Videos
- Blog: Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin
- Blog: The IRST English-Spanish translation system for european parliament speeches
- Blog: MathReader : Text-to-Speech for Mathematical Documents
- Blog: A language-modeling approach to inverse text normalization and data cleanup for multimodal voice search applications
- Blog: The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring
- Blog: A system for automatic broadcast news summarisation, geolocation and translation
- Blog: Automated production of true-cased punctuated subtitles for weather and news broadcasts
- Blog: Streaming, Fast and Accurate on-Device Inverse Text Normalization for Automatic Speech Recognition
- Blog: Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translation
- Blog: Development of SRI's translation systems for broadcast news and broadcast conversations
- Blog: The RWTH Aachen machine translation systems for IWSLT 2013
- Blog: Combined spoken language translation
- Blog: Adapting Whisper for Regional Dialects: Enhancing Public Services for Vulnerable Populations in the United Kingdom
- Blog: Improving Readability for Automatic Speech Recognition Transcription
- Blog: Multilingual End-to-End Speech Translation
- Blog: unimelb: Spanish Text Normalisation
- Blog: Automatic Punctuation Model for Spanish Live Transcriptions
- Blog: KIT’s IWSLT 2021 Offline Speech Translation System
- Blog: Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
- Blog: THE IWSLT 2021 BUT SPEECH TRANSLATION SYSTEMS
- Blog: The USYD-JD Speech Translation System for IWSLT2021
- Blog: LIMSI English-French speech translation system
- Blog: Combination of NN and CRF models for joint detection of punctuation and disfluencies
- Blog: Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcripts
- Blog: BTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text
- Blog: Simple and Effective Unsupervised Speech Translation
- Blog: Unlocking Speech Instruction Data Potential with Query Rewriting
- Blog: FBK @ IWSLT 2011
- Blog: The CUED HiFST System for the WMT10 Translation Shared Task
- Blog: MultiTurnCleanup: A Benchmark for Multi-Turn Spoken Conversational Transcript Cleanup
Showing 60 of 91 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_asr_output_normalization_4e044f8a,
title = {ASR output normalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asr-output-normalization/rdr_4e044f8acdf64d12a12908d119128218},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_asr_output_normalization_4e044f8a_v2,
title = {ASR output normalization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asr-output-normalization/rdr_4e044f8acdf64d12a12908d119128218/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}