Picture for Van Tung Pham

Van Tung Pham

RdimKD: Generic Distillation Paradigm by Dimensionality Reduction

Add code
Dec 14, 2023
Viaarxiv icon

Improving short-video speech recognition using random utterance concatenation

Oct 28, 2022
Figure 1 for Improving short-video speech recognition using random utterance concatenation
Figure 2 for Improving short-video speech recognition using random utterance concatenation
Figure 3 for Improving short-video speech recognition using random utterance concatenation
Figure 4 for Improving short-video speech recognition using random utterance concatenation
Viaarxiv icon

Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech

Add code
Jul 22, 2021
Figure 1 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 2 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 3 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Figure 4 for Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
Viaarxiv icon

End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN

Jan 13, 2021
Figure 1 for End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN
Figure 2 for End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN
Figure 3 for End-to-End Speaker Height and age estimation using Attention Mechanism with LSTM-RNN
Viaarxiv icon

Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning

May 28, 2020
Figure 1 for Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning
Figure 2 for Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning
Figure 3 for Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning
Figure 4 for Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning
Viaarxiv icon

Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems

Add code
May 18, 2020
Figure 1 for Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems
Figure 2 for Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems
Figure 3 for Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems
Viaarxiv icon

Independent language modeling architecture for end-to-end ASR

Nov 25, 2019
Figure 1 for Independent language modeling architecture for end-to-end ASR
Figure 2 for Independent language modeling architecture for end-to-end ASR
Figure 3 for Independent language modeling architecture for end-to-end ASR
Figure 4 for Independent language modeling architecture for end-to-end ASR
Viaarxiv icon

Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data

Add code
Apr 08, 2019
Figure 1 for Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
Figure 2 for Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
Figure 3 for Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
Figure 4 for Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
Viaarxiv icon

Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation

Add code
Apr 08, 2019
Figure 1 for Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
Figure 2 for Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
Figure 3 for Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
Figure 4 for Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
Viaarxiv icon

On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition

Add code
Nov 01, 2018
Figure 1 for On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
Figure 2 for On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
Figure 3 for On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
Figure 4 for On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
Viaarxiv icon