[MULTILINGUAL SPEECH RECOGNITION WITH A SINGLE END-TO-END MODEL ](https://jointphd.notion.site/MULTILINGUAL-SPEECH-RECOGNITION-WITH-A-SINGLE-END-TO-END-MODEL-3ec994ee3fbd430a847c5abfcc08cf72)

[Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model](https://jointphd.notion.site/Large-Scale-Multilingual-Speech-Recognition-with-a-Streaming-End-to-End-Model-f77eda13cff5470c95fd3e3b260ab415)

[EXPLORING ARCHITECTURES, DATA AND UNITS FOR STREAMING END TO-END SPEECH RECOGNITION WITH RNN-TRANSDUCER](https://jointphd.notion.site/EXPLORING-ARCHITECTURES-DATA-AND-UNITS-FOR-STREAMING-END-TO-END-SPEECH-RECOGNITION-WITH-RNN-TRANSDU-649f6f555c954e1fa55731055157a5d6)

[Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters ](https://jointphd.notion.site/Massively-Multilingual-ASR-50-Languages-1-Model-1-Billion-Parameters-7e893ef47f3b41bba997360f2ad8c17f)

[Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages](https://jointphd.notion.site/Multilingual-End-to-End-Speech-Recognition-with-A-Single-Transformer-on-Low-Resource-Languages-1d811ec47d1245f4b62ddddea06e8e21)

[Multilingual and code-switching ASR challenges for low resource Indian languages](https://jointphd.notion.site/Multilingual-and-code-switching-ASR-challenges-for-low-resource-Indian-languages-02709a6c2103436ca3db35eb4975a159)

[UNSUPERVISED PRETRAINING TRANSFERS WELL ACROSS LANGUAGES ](https://jointphd.notion.site/UNSUPERVISED-PRETRAINING-TRANSFERS-WELL-ACROSS-LANGUAGES-7b78001d78b0446497143c2bc7efe86a)

[Towards Building ASR Systems for the Next Billion Users ](https://jointphd.notion.site/Towards-Building-ASR-Systems-for-the-Next-Billion-Users-d584ef6035e34375ab5006b31b2b2c2e)

[UNSUPERVISED CROSS-LINGUAL REPRESENTATION LEARNING FOR SPEECH RECOGNITION](https://jointphd.notion.site/UNSUPERVISED-CROSS-LINGUAL-REPRESENTATION-LEARNING-FOR-SPEECH-RECOGNITION-15f66093dd7242d2b31036a2ed9a178e)

[APPLYING WAV2VEC2.0 TO SPEECH RECOGNITION IN VARIOUS LOW-RESOURCE LANGUAGES](https://jointphd.notion.site/APPLYING-WAV2VEC2-0-TO-SPEECH-RECOGNITION-IN-VARIOUS-LOW-RESOURCE-LANGUAGES-b588f910bb744c9e807a9829a05f4baf)

[SCALING ASR IMPROVES ZERO AND FEW SHOT LEARNING ](https://jointphd.notion.site/SCALING-ASR-IMPROVES-ZERO-AND-FEW-SHOT-LEARNING-6e689c75979e4f23b6cdd57825d6a09c)

[MULTILINGUAL MLP FEATURES FOR LOW-RESOURCE LVCSR SYSTEMS](https://jointphd.notion.site/MULTILINGUAL-MLP-FEATURES-FOR-LOW-RESOURCE-LVCSR-SYSTEMS-7bf1302803d74825b714a293d1e30aa0)

Cross-lingual and multi-stream posterior features for low resource LVCSR systems.

[MULTILINGUAL TRAINING OF DEEP NEURAL NETWORKS ](https://jointphd.notion.site/MULTILINGUAL-TRAINING-OF-DEEP-NEURAL-NETWORKS-497acaa25c914a25a40b82d1bd769979)

[MULTILINGUAL ACOUSTIC MODELS USING DISTRIBUTED DEEP NEURAL NETWORKS ](https://jointphd.notion.site/MULTILINGUAL-ACOUSTIC-MODELS-USING-DISTRIBUTED-DEEP-NEURAL-NETWORKS-8b469e7ef639437b8f9c70bdbcf9917d)

[KNOWLEDGE DISTILLATION ACROSS ENSEMBLES OF MULTILINGUAL MODELS FOR LOW-RESOURCE LANGUAGES](https://jointphd.notion.site/KNOWLEDGE-DISTILLATION-ACROSS-ENSEMBLES-OF-MULTILINGUAL-MODELS-FOR-LOW-RESOURCE-LANGUAGES-102d9cbc2a08465cb431197d21a22c87)

[Context independent/dependent acoustic modelling. ](https://jointphd.notion.site/Context-independent-dependent-acoustic-modelling-ef10fe37b09342beb7696d3a8a8cab7a)

[END-TO-END ASR: FROM SUPERVISED TO SEMI-SUPERVISED LEARNING WITH MODERN ARCHITECTURE](https://jointphd.notion.site/END-TO-END-ASR-FROM-SUPERVISED-TO-SEMI-SUPERVISED-LEARNING-WITH-MODERN-ARCHITECTURE-0fd202a68b3d4049ac0ac0e0d7fbf075)

[Automatic speech recognition for under-resourced languages: A survey](https://jointphd.notion.site/Automatic-speech-recognition-for-under-resourced-languages-A-survey-b836415b29134cddb402ce39ae2b842e)