| # Publications | |
| Here, we list a collection of research articles that utilize the NeMo Toolkit. If you would like to include your paper in this collection, please submit a PR updating this document. | |
| ------- | |
| # Automatic Speech Recognition (ASR) | |
| <details> | |
| <summary>2023</summary> | |
| * [Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-to-End Automatic Speech Recognition](https://ieeexplore.ieee.org/abstract/document/10022960) | |
| * [Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition](https://ieeexplore.ieee.org/abstract/document/10023219) | |
| </details> | |
| <details> | |
| <summary>2022</summary> | |
| * [Multi-blank Transducers for Speech Recognition](https://arxiv.org/abs/2211.03541) | |
| </details> | |
| <details> | |
| <summary>2021</summary> | |
| * [Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition](https://arxiv.org/abs/2104.01721) | |
| * [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://www.isca-speech.org/archive/interspeech_2021/oneill21_interspeech.html) | |
| * [CarneliNet: Neural Mixture Model for Automatic Speech Recognition](https://arxiv.org/abs/2107.10708) | |
| * [CTC Variations Through New WFST Topologies](https://arxiv.org/abs/2110.03098) | |
| * [A Toolbox for Construction and Analysis of Speech Datasets](https://openreview.net/pdf?id=oJ0oHQtAld) | |
| </details> | |
| <details> | |
| <summary>2020</summary> | |
| * [Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition](https://ieeexplore.ieee.org/document/9428334) | |
| * [Correction of Automatic Speech Recognition with Transformer Sequence-To-Sequence Model](https://ieeexplore.ieee.org/abstract/document/9053051) | |
| * [Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition](https://arxiv.org/abs/2010.12715) | |
| </details> | |
| <details> | |
| <summary>2019</summary> | |
| * [Jasper: An End-to-End Convolutional Neural Acoustic Model](https://arxiv.org/abs/1904.03288) | |
| * [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://arxiv.org/abs/1910.10261) | |
| </details> | |
| -------- | |
| ## Speaker Recognition (SpkR) | |
| <details> | |
| <summary>2022</summary> | |
| * [TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context](https://ieeexplore.ieee.org/abstract/document/9746806) | |
| </details> | |
| <details> | |
| <summary>2020</summary> | |
| * [SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification]( https://arxiv.org/pdf/2010.12653.pdf) | |
| </details> | |
| -------- | |
| ## Speech Classification | |
| <details> | |
| <summary>2022</summary> | |
| * [AmberNet: A Compact End-to-End Model for Spoken Language Identification](https://arxiv.org/abs/2210.15781) | |
| * [Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models](https://arxiv.org/abs/2211.05103) | |
| </details> | |
| <details> | |
| <summary>2021</summary> | |
| * [MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection](https://ieeexplore.ieee.org/abstract/document/9414470/) | |
| </details> | |
| <details> | |
| <summary>2020</summary> | |
| * [MatchboxNet - 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition](http://www.interspeech2020.org/index.php?m=content&c=index&a=show&catid=337&id=993) | |
| </details> | |
| -------- | |
| ## Speech Translation | |
| <details> | |
| <summary>2022</summary> | |
| * [NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2022](https://aclanthology.org/2022.iwslt-1.18/) | |
| </details> | |
| -------- | |
| # Natural Language Processing (NLP) | |
| ## Language Modeling | |
| <details> | |
| <summary>2022</summary> | |
| * [Evaluating Parameter Efficient Learning for Generation](https://arxiv.org/abs/2210.13673) | |
| * [Text Mining Drug/Chemical-Protein Interactions using an Ensemble of BERT and T5 Based Models](https://arxiv.org/abs/2111.15617) | |
| </details> | |
| <details> | |
| <summary>2021</summary> | |
| * [BioMegatron: Larger Biomedical Domain Language Model ](https://aclanthology.org/2020.emnlp-main.379/) | |
| </details> | |
| ## Neural Machine Translation | |
| <details> | |
| <summary>2022</summary> | |
| * [Finding the Right Recipe for Low Resource Domain Adaptation in Neural Machine Translation](https://arxiv.org/abs/2206.01137) | |
| </details> | |
| <details> | |
| <summary>2021</summary> | |
| * [NVIDIA NeMo Neural Machine Translatio Systems for English-German and English-Russian News and Biomedical Tasks at WMT21](https://arxiv.org/pdf/2111.08634.pdf) | |
| </details> | |
| -------- | |
| ## Dialogue State Tracking | |
| <details> | |
| <summary>2021</summary> | |
| * [SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services](https://arxiv.org/abs/2105.08049) | |
| </details> | |
| <details> | |
| <summary>2020</summary> | |
| * [A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset](https://arxiv.org/abs/2008.12335) | |
| </details> | |
| -------- | |
| # Text To Speech (TTS) | |
| <details> | |
| <summary>2022</summary> | |
| * [Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers](https://arxiv.org/abs/2211.00585) | |
| </details> | |
| <details> | |
| <summary>2021</summary> | |
| * [TalkNet: Fully-Convolutional Non-Autoregressive Speech Synthesis Model](https://www.isca-speech.org/archive/interspeech_2021/beliaev21_interspeech.html) | |
| * [TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction](https://arxiv.org/abs/2104.08189) | |
| * [Hi-Fi Multi-Speaker English TTS Dataset](https://www.isca-speech.org/archive/pdfs/interspeech_2021/bakhturina21_interspeech.pdf) | |
| * [Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings](https://arxiv.org/abs/2110.03584) | |
| </details> | |
| -------- | |
| # (Inverse) Text Normalization | |
| <details> | |
| <summary>2022</summary> | |
| * [Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization](https://arxiv.org/abs/2203.15917) | |
| * [Thutmose Tagger: Single-pass neural model for Inverse Text Normalization](https://arxiv.org/abs/2208.00064) | |
| </details> | |
| <details> | |
| <summary>2021</summary> | |
| * [NeMo Inverse Text Normalization: From Development to Production](https://www.isca-speech.org/archive/pdfs/interspeech_2021/zhang21ga_interspeech.pdf) | |
| * [A Unified Transformer-based Framework for Duplex Text Normalization](https://arxiv.org/pdf/2108.09889.pdf ) | |
| </details> | |
| -------- |