From c91855e18ecdcb714ed44fb0e2e67aaaa56cec6b Mon Sep 17 00:00:00 2001 From: Somshubra Majumdar Date: Tue, 7 Feb 2023 18:02:44 -0800 Subject: [PATCH 1/4] Add papers from 2022/2022 to PUBLICATIONS.md Signed-off-by: smajumdar --- PUBLICATIONS.md | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/PUBLICATIONS.md b/PUBLICATIONS.md index 67c7cd11084b..1a819f1efa43 100644 --- a/PUBLICATIONS.md +++ b/PUBLICATIONS.md @@ -6,6 +6,22 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I # Automatic Speech Recognition (ASR) +
+ 2023 + + * [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) + +
+ +
+ 2022 + + * [Multi-blank Transducers for Speech Recognition](https://arxiv.org/abs/2211.03541) + * [Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models](https://arxiv.org/abs/2211.05103) + +
+
2021 @@ -14,6 +30,7 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I * [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) + *
@@ -44,9 +61,9 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I ## Speaker Recognition (SpkR)
- 2021 + 2022 - * [TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context]( https://arxiv.org/pdf/2110.04410.pdf) + * [TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context](https://ieeexplore.ieee.org/abstract/document/9746806)
@@ -122,6 +139,14 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I # Text To Speech (TTS) +
+ 2022 + + * [Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers](https://arxiv.org/abs/2211.00585) + * + +
+
2021 @@ -140,6 +165,7 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I 2022 * [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)
From acd75412f0c8b897e4b0718d45f9ab081ecd1cdd Mon Sep 17 00:00:00 2001 From: Somshubra Majumdar Date: Tue, 7 Feb 2023 18:08:29 -0800 Subject: [PATCH 2/4] Remove ipynb from being tracked as for nemo code library Signed-off-by: smajumdar --- .gitignore | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/.gitignore b/.gitignore index 0ecdaa49ec94..1ff2a92cac64 100644 --- a/.gitignore +++ b/.gitignore @@ -94,6 +94,10 @@ target/ # Jupyter Notebook .ipynb_checkpoints +# Override Jupyter in Github Language states for more accurate estimate of repo code. +# Reference: https://github.com/github/linguist/blob/master/docs/overrides.md#generated-code +*.ipynb linguist-generated + # IPython profile_default/ ipython_config.py From 9c1133a7cd799b73ac66de3b17ebd65768d6b327 Mon Sep 17 00:00:00 2001 From: Somshubra Majumdar Date: Tue, 7 Feb 2023 18:11:45 -0800 Subject: [PATCH 3/4] Remove ipynb from being tracked as for nemo code library Signed-off-by: smajumdar --- PUBLICATIONS.md | 2 -- 1 file changed, 2 deletions(-) diff --git a/PUBLICATIONS.md b/PUBLICATIONS.md index 1a819f1efa43..0467c1228ff2 100644 --- a/PUBLICATIONS.md +++ b/PUBLICATIONS.md @@ -30,7 +30,6 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I * [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) - * @@ -143,7 +142,6 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I 2022 * [Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers](https://arxiv.org/abs/2211.00585) - * From 88d7c4a92bceae70b5c2a44f1497d1ca9d2783cb Mon Sep 17 00:00:00 2001 From: Somshubra Majumdar Date: Wed, 8 Feb 2023 13:25:19 -0800 Subject: [PATCH 4/4] Add additional papers Signed-off-by: smajumdar --- PUBLICATIONS.md | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/PUBLICATIONS.md b/PUBLICATIONS.md index 0467c1228ff2..365ed2773ed3 100644 --- a/PUBLICATIONS.md +++ b/PUBLICATIONS.md @@ -18,7 +18,6 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I 2022 * [Multi-blank Transducers for Speech Recognition](https://arxiv.org/abs/2211.03541) - * [Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models](https://arxiv.org/abs/2211.05103) @@ -78,6 +77,15 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I ## Speech Classification +
+ 2022 + + * [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) + + +
+
2021 @@ -94,12 +102,32 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I
+-------- + +## Speech Translation + +
+ 2022 + + * [NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2022](https://aclanthology.org/2022.iwslt-1.18/) + +
+ + -------- # Natural Language Processing (NLP) ## Language Modeling +
+ 2022 + + * [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) + +
+
2021 @@ -109,6 +137,13 @@ Here, we list a collection of research articles that utilize the NeMo Toolkit. I ## Neural Machine Translation +
+ 2022 + + * [Finding the Right Recipe for Low Resource Domain Adaptation in Neural Machine Translation](https://arxiv.org/abs/2206.01137) + +
+
2021