No article text was recorded for this version.
serialized output training
Version 2 of 274 papers103 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Streaming Multi-Talker ASR with Token-Level Serialized Output Training
- Blog: Serialized Output Training for End-to-End Overlapped Speech Recognition
- Blog: Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR
- Blog: Behavior-SD: Behaviorally Aware Spoken Dialogue Generation with Large Language Models
- Blog: Adapting Multi-Lingual ASR Models for Handling Multiple Talkers
- Blog: Summary On The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge
- Blog: MoonCast: High-Quality Zero-Shot Podcast Generation
- Blog: End-to-End Joint Target and Non-Target Speakers ASR
- Blog: Directional Speech Recognition for Speaker Disambiguation and Cross-talk Suppression
- Blog: Cascaded encoders for fine-tuning ASR models on overlapped speech
- Blog: Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge
- Blog: The Volcspeech System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
- Blog: Streaming end-to-end multi-talker speech recognition
- Blog: M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
- Blog: Translatotron 2: High-quality direct speech-to-speech translation with voice preservation
- Blog: Serialized Output Training for End-to-End Overlapped Speech Recognition
- Blog: Adapting Multi-Lingual ASR Models for Handling Multiple Talkers
- Blog: Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone
- Blog: A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings
- Blog: t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability
- Blog: Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone
- Blog: LibriheavyMix: A 20, 000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
- Blog: Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios
- Blog: Streaming Multi-Talker Speech Recognition with Joint Speaker Identification
- Blog: SOMSRED: Sequential Output Modeling for Joint Multi-talker Overlapped Speech Recognition and Speaker Diarization
- Blog: Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings
- Blog: Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition
- Blog: NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription
- Blog: Multimodal Speaker Segmentation and Diarization Using Lexical and Acoustic Cues via Sequence to Sequence Neural Networks
- Blog: Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
- Blog: SA-Paraformer: Non-autoregressive End-to-End Speaker-Attributed ASR
- Blog: NeMo Open Source Speaker Diarization System
- Blog: One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition
- Blog: Speech Recognition and Multi-Speaker Diarization of Long Conversations
- Blog: End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
- Blog: Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers
- Blog: AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition
- Blog: Joint Speech Recognition and Speaker Diarization via Sequence Transduction
- Blog: Joint Autoregressive Modeling of End-to-End Multi-Talker Overlapped Speech Recognition and Utterance-level Timestamp Prediction
- Blog: SOT Triggered Neural Clustering for Speaker Attributed ASR
- Blog: BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR
- Blog: Adapting self-supervised models to multi-talker speech recognition using speaker embeddings
- Blog: Joint vs Sequential Speaker-Role Detection and Automatic Speech Recognition for Air-traffic Control
- Blog: LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
- Blog: Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings
- Blog: Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation
- Blog: End-to-End Multi-speaker Speech Recognition with Transformer
- Blog: Context-aware RNNLM Rescoring for Conversational Speech Recognition
- Blog: Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition
- Blog: Advancing Multi-talker ASR Performance with Large Language Models
- Blog: DiariST: Streaming Speech Translation with Speaker Diarization
- Blog: End-to-End Speaker-Attributed ASR with Transformer
- Blog: Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition
- Blog: VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition
- Blog: CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models
- Blog: Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of any Number of Speakers
- Blog: Serialized Output Training by Learned Dominance
- Blog: LEAP Submission for the Third DIHARD Diarization Challenge
- Blog: CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
- Blog: Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
Showing 60 of 74 papers.
History & citation
Current · Permanent link
- Chronological Labeling for Multi-Talker Speech Recognition merged into this direction (55% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_serialized_output_training_5fe5972b,
title = {serialized output training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/serialized-output-training/rdr_5fe5972b0c3543bb9b5be127bcccfc0b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_serialized_output_training_5fe5972b_v2,
title = {serialized output training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/serialized-output-training/rdr_5fe5972b0c3543bb9b5be127bcccfc0b/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}