algorithms (1) books (1) chime6 (1) conference (4) conference summary (2) css (1) deep learning (11) dialog system (1) diarization (1) evaluation (1) expectation maximization (1) feature extraction (1) gbo (13) general (1) gss (1) i-vectors (1) kaldi (4) lattice-free MMI (1) learning theory (7) machine learning (3) machine translation (2) machine-learning (3) maxent (1) ml-basics (5) multimodal (1) mvdr (1) natural language generation (1) natural language processing (9) natural-language-processing (1) online learning (2) optimization (2) representation learning (5) research (1) semantic parsing (2) speaker diarization (1) spectral clustering (1) speech enhancement (1) speech processing (4) speech recognition (6) speech-recognition (2) subword (1) test (2) text classification (1) transfer learning (1) transformer (2) variational bayes (1)

 algorithms (1)

GBO notes: Approximation algorithms

 books (1)

Flake it till you make it

 chime6 (1)

Understanding the JHU CHiME-6 Submission - Part I (Enhancement)

 conference (4)

My 3 takeaways from IEEE ICASSP 2021
Desh's curated list of ASR, diarization, and related papers from Interspeech 2020
Some interesting papers from ASRU 2019
Highlights from SANE 2019

 conference summary (2)

ACL 2019: Notes from an ASR perspective
The Best Papers at ICLR 2017

 css (1)

GBO notes: Continuous speech separation

 deep learning (11)

A round-up of linear transformers
Theory of Deep Learning: An Illustration with Embeddings
Theory of Deep Learning: Generative Models
Theory of Deep Learning: Role of Depth
Theory of Deep Learning: Generalization
Theory of Deep Learning: Optimization
Unsupervised Approaches for NMT
Deep Learning for Multimodal Systems
The Best Papers at ICLR 2017
The Last 3 Years in Text Classification
Understanding Word Vectors

 dialog system (1)

Evaluation Methods for Dialog Systems

 diarization (1)

On the evaluation of speaker diarization systems

 evaluation (1)

On the evaluation of speaker diarization systems

 expectation maximization (1)

GBO notes: Expectation Maximization

 feature extraction (1)

A note on MFCCs and delta features

 gbo (13)

GBO notes: Approximation algorithms
GBO notes: Machine learning basics (Part 5)
GBO notes: Machine learning basics (Part 4)
GBO notes: Machine learning basics (Part 3)
GBO notes: Machine learning basics (Part 2)
GBO notes: Machine learning basics (Part 1)
GBO notes: Continuous speech separation
GBO notes: MVDR beamforming
GBO notes: Mask estimation for GSS
GBO notes: Variational Bayes and the VBx algorithm
GBO notes: Spectral clustering
GBO notes: i-vectors and x-vectors
GBO notes: Expectation Maximization

 general (1)

Heilmeier Catachism of my research

 gss (1)

GBO notes: Mask estimation for GSS

 i-vectors (1)

GBO notes: i-vectors and x-vectors

 kaldi (4)

How to use the pre-trained Librispeech model in Kaldi
A note on MFCCs and delta features
On lattice free MMI and Chain models in Kaldi
Some Kaldi Things

 lattice-free MMI (1)

On lattice free MMI and Chain models in Kaldi

 learning theory (7)

Theory of Deep Learning: An Illustration with Embeddings
Theory of Deep Learning: Generative Models
Theory of Deep Learning: Role of Depth
Theory of Deep Learning: Generalization
Theory of Deep Learning: Optimization
Introduction to Learning Theory - Part 2
Introduction to Learning Theory - Part 1

 machine learning (3)

An Introduction to Speech Recognition using WFSTs
Sparsity in Online Learning with Lasso Regularization
A Short Note on Stochastic Gradient Descent Algorithms

 machine translation (2)

Unsupervised Approaches for NMT
Metrics for NLG Evaluation

 machine-learning (3)

Iterative Scaling and Coordinate Descent
Experiments with Subword Modeling
Award-winning classic papers in ML and NLP

 maxent (1)

Iterative Scaling and Coordinate Descent

 ml-basics (5)

GBO notes: Machine learning basics (Part 5)
GBO notes: Machine learning basics (Part 4)
GBO notes: Machine learning basics (Part 3)
GBO notes: Machine learning basics (Part 2)
GBO notes: Machine learning basics (Part 1)

 multimodal (1)

Deep Learning for Multimodal Systems

 mvdr (1)

GBO notes: MVDR beamforming

 natural language generation (1)

Metrics for NLG Evaluation

 natural language processing (9)

ACL 2019: Notes from an ASR perspective
Transfer Learning in NLP
Irony Detection in Tweets
Unsupervised Approaches for NMT
Trends in Semantic Parsing - Part 2
The Last 3 Years in Text Classification
Understanding Word Vectors
Trends in Semantic Parsing - Part 1
Metrics for NLG Evaluation

 natural-language-processing (1)

Award-winning classic papers in ML and NLP

 online learning (2)

Online Learning of Word Embeddings
Sparsity in Online Learning with Lasso Regularization

 optimization (2)

Iterative Scaling and Coordinate Descent
A Short Note on Stochastic Gradient Descent Algorithms

 representation learning (5)

How to Obtain Sentence Vectors
Online Learning of Word Embeddings
Irony Detection in Tweets
Beyond Euclidean Embeddings
Understanding Word Vectors

 research (1)

The 8 Commandments for Coding Your Research

 semantic parsing (2)

Trends in Semantic Parsing - Part 2
Trends in Semantic Parsing - Part 1

 speaker diarization (1)

Understanding the JHU CHiME-6 Submission - Part I (Enhancement)

 spectral clustering (1)

GBO notes: Spectral clustering

 speech enhancement (1)

Understanding the JHU CHiME-6 Submission - Part I (Enhancement)

 speech processing (4)

My 3 takeaways from IEEE ICASSP 2021
Desh's curated list of ASR, diarization, and related papers from Interspeech 2020
Some interesting papers from ASRU 2019
Highlights from SANE 2019

 speech recognition (6)

Understanding the JHU CHiME-6 Submission - Part I (Enhancement)
How to use the pre-trained Librispeech model in Kaldi
The Challenges of using Transformers in ASR
A Reading List for Automatic Speech Recognition
ACL 2019: Notes from an ASR perspective
An Introduction to Speech Recognition using WFSTs

 speech-recognition (2)

A note on MFCCs and delta features
Experiments with Subword Modeling

 subword (1)

Experiments with Subword Modeling

 test (2)

Sample blog post
Flake it till you make it

 text classification (1)

The Last 3 Years in Text Classification

 transfer learning (1)

Transfer Learning in NLP

 transformer (2)

A round-up of linear transformers
The Challenges of using Transformers in ASR

 variational bayes (1)

GBO notes: Variational Bayes and the VBx algorithm