awesome-asr-contextualization
A curated list of awesome papers on contextualizing E2E ASR outputs
https://github.com/stevenhillis/awesome-asr-contextualization
Last synced: 18 days ago
JSON representation
Deep Contextualization
2021
- Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition
- Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
2022
- Improving End-to-End Contextual Speech Recognition with Fine-grained Contextual Knowledge Selection
- End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system
- Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems
Contextual LAS (CLAS)
- Phoebe: Pronunciation-aware Contextualization for End-to-end Speech Recognition
- Joint Grapheme and Phoneme Embeddings for Contextual End-to-End ASR
- Deep context: end-to-end contextual speech recognition
- Contextual Speech Recognition with Difficult Negative Training Examples
- Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models
Contextual Transducer ("RNNTs")
- Multistate Encoding with End-To-End Speech RNN Transducer Network
- Contextual RNN-T For Open Domain ASR
- Deep Shallow Fusion for RNN-T Personalization
- Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
- Context-Aware Transformer Transducer for Speech Recognition
- Contextual Adapters for Personalized Speech Recognition in Neural Transducers
- Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer
- Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition
External Contextualization
2012
2015
- Composition-based on-the-fly rescoring for salient n-gram biasing
- Improved recognition of contact names in voice commands
2016
2017
2018
- Contextual speech recognition in end-to-end neural network systems using beam search
- Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition
- End-to-end contextual speech recognition using class language models and a token passing decoder
2019
- Contextual Recovery of Out-of-Lattice Named Entities in Automatic Speech Recognition
- Shallow-Fusion End-to-End Contextual Biasing
- Bangla Voice Command Recognition in end-to-end System Using Topic Modeling based Contextual Rescoring
- Incorporating Written Domain Numeric Grammars into End-To-End Contextual Speech Recognition Systems for Improved Recognition of Numeric Sequences
- Hierarchical Multi-Stage Word-to-Grapheme Named Entity Corrector for Automatic Speech Recognition
- Personalization of End-to-End Speech Recognition on Mobile Devices for Named Entities
- Joint Contextual Modeling for ASR Correction and Language Understanding
- Fast and Robust Unsupervised Contextual Biasing for Speech Recognition
- Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model
- Class LM and word mapping for contextual biasing in End-to-End ASR
- Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion
- Rapid RNN-T Adaptation Using Personalized Speech Synthesis and Neural Language Generator
2021
- Domain-Aware Neural Language Models for Speech Recognition
- Personalization Strategies for End-to-End Speech Recognition Systems
- A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems
- Spell my name: keyword boosted speech recognition