1 |
Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Nonlinear ISA with Auxiliary Variables for Learning Speech Representations ...
|
|
|
|
Abstract:
This paper extends recent work on nonlinear Independent Component Analysis (ICA) by introducing a theoretical framework for nonlinear Independent Subspace Analysis (ISA) in the presence of auxiliary variables. Observed high dimensional acoustic features like log Mel spectrograms can be considered as surface level manifestations of nonlinear transformations over individual multivariate sources of information like speaker characteristics, phonological content etc. Under assumptions of energy based models we use the theory of nonlinear ISA to propose an algorithm that learns unsupervised speech representations whose subspaces are independent and potentially highly correlated with the original non-stationary multivariate sources. We show how nonlinear ICA with auxiliary variables can be extended to a generic identifiable model for subspaces as well while also providing sufficient conditions for the identifiability of these high dimensional subspaces. Our proposed methodology is generic and can be integrated with ... : To be presented at Interspeech 2020 ...
|
|
Keyword:
Audio and Speech Processing eess.AS; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG; Machine Learning stat.ML; Sound cs.SD
|
|
URL: https://dx.doi.org/10.48550/arxiv.2007.12948 https://arxiv.org/abs/2007.12948
|
|
BASE
|
|
Hide details
|
|
10 |
Towards Minimal Supervision BERT-based Grammar Error Correction ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Towards Zero-shot Learning for Automatic Phonemic Transcription ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Automatically Identifying Language Family from Acoustic Examples in Low Resource Scenarios ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Mere account mein kitna balance hai? -- On building voice enabled Banking Services for Multilingual Communities ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Universal Phone Recognition with a Multilingual Allophone System ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|