# Speech recognition models and training

Area: [Speech and audio language models](https://mlsanity.com/speech/index.md). HTML: https://mlsanity.com/speech/speech-recognition-models-and-training/

## Key facts

- Speech recognition models and training: 1,811 papers on arXiv since 2021 (data through 19 Oct 2026).
- 448 of its 1,811 mapped papers (25%) cite “Robust Speech Recognition via Large-Scale Weak Supervision” (2022, arXiv 2212.04356).
- 242 of its 1,811 mapped papers (13%) cite “WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing” (2021, arXiv 2110.13900).
- 20 new papers 2 Oct–19 Oct.

## Most cited here

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022), cited by 448 papers here
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021), cited by 242 papers here
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021), cited by 95 papers here
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021), cited by 94 papers here
- [WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2102.01547/) (2021), cited by 86 papers here
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022), cited by 74 papers here
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023), cited by 71 papers here
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021), cited by 67 papers here
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021), cited by 67 papers here
- [Prompting Large Language Models with Speech Recognition Abilities](https://mlsanity.com/paper/2307.11795/) (2023), cited by 65 papers here

## New (2 Oct–19 Oct)

- [Preference-Aware Pareto Steering for Multi-Task Speech LLMs](https://mlsanity.com/paper/2610.27200/) (2026-10-19)
- [Think Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech Recognition](https://mlsanity.com/paper/2610.26986/) (2026-10-19)
- [PronCFT: Pronunciation Contextual Fine-Tuning for Contextual Biasing of Out-of-Vocabulary Words in LLM-Based ASR](https://mlsanity.com/paper/2610.25766/) (2026-10-19)
- [Ask, Don't Guess: Targeted Clarification for Speech Recognition Errors](https://mlsanity.com/paper/2610.24809/) (2026-10-17)
- [Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation](https://mlsanity.com/paper/2610.23409/) (2026-10-16)
- [Zero-Shot Spoken Language Understanding with SLAM-ASR: What Do Monolingual ASR-Trained Linear Projectors Enable?](https://mlsanity.com/paper/2610.20844/) (2026-10-14)
- [Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy](https://mlsanity.com/paper/2610.19492/) (2026-10-14)
- [SSEmb: Training a Generalizable Speech Retrieval Model Using Only Automatic Speech Recognition Data](https://mlsanity.com/paper/2610.17813/) (2026-10-13)
- [Towards Privacy-Preserving ASR: Speaker-Level Machine Unlearning](https://mlsanity.com/paper/2610.16196/) (2026-10-12)
- [Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses](https://mlsanity.com/paper/2610.15056/) (2026-10-10)
- [ASSET: Adaptive Speech Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2610.14309/) (2026-10-09)
- [Lossless Inference Acceleration for ASR via EAGLE-Style Speculative Decoding](https://mlsanity.com/paper/2610.13506/) (2026-10-09)
- [O'ido: Open-Vocabulary Speech Recognition on a 5 Microcontroller without a Neural Accelerator](https://mlsanity.com/paper/2610.13447/) (2026-10-09)
- [Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR](https://mlsanity.com/paper/2610.13432/) (2026-10-09)
- [From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale](https://mlsanity.com/paper/2610.13102/) (2026-10-09)
- [When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech Parsing](https://mlsanity.com/paper/2610.11520/) (2026-10-08)
- [DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs](https://mlsanity.com/paper/2610.08085/) (2026-10-06)
- [HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR](https://mlsanity.com/paper/2610.08063/) (2026-10-06)
- [Lyric: Wave-Domain Computing for Efficient Spoken-Digit Recognition](https://mlsanity.com/paper/2610.06433/) (2026-10-05)
- [Factorized Delayed Streams Modeling for LLM-based Streaming ASR](https://mlsanity.com/paper/2610.04333/) (2026-10-03)