Picture for Dongji Gao

Dongji Gao

Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition

Add code
Sep 26, 2023
Figure 1 for Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
Figure 2 for Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
Figure 3 for Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
Figure 4 for Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
Viaarxiv icon

Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition

Add code
Aug 12, 2023
Figure 1 for Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition
Figure 2 for Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition
Figure 3 for Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition
Figure 4 for Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition
Viaarxiv icon

HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation

Add code
Jun 20, 2023
Figure 1 for HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
Figure 2 for HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
Figure 3 for HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
Figure 4 for HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
Viaarxiv icon

Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts

Add code
Jun 01, 2023
Figure 1 for Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
Figure 2 for Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
Figure 3 for Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
Figure 4 for Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts
Viaarxiv icon

PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor

Add code
Mar 15, 2023
Figure 1 for PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor
Figure 2 for PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor
Figure 3 for PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor
Figure 4 for PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with Phoneme Distribution Predictor
Viaarxiv icon

EURO: ESPnet Unsupervised ASR Open-source Toolkit

Add code
Dec 01, 2022
Figure 1 for EURO: ESPnet Unsupervised ASR Open-source Toolkit
Figure 2 for EURO: ESPnet Unsupervised ASR Open-source Toolkit
Figure 3 for EURO: ESPnet Unsupervised ASR Open-source Toolkit
Figure 4 for EURO: ESPnet Unsupervised ASR Open-source Toolkit
Viaarxiv icon

Bridging Speech and Textual Pre-trained Models with Unsupervised ASR

Add code
Nov 06, 2022
Figure 1 for Bridging Speech and Textual Pre-trained Models with Unsupervised ASR
Figure 2 for Bridging Speech and Textual Pre-trained Models with Unsupervised ASR
Figure 3 for Bridging Speech and Textual Pre-trained Models with Unsupervised ASR
Figure 4 for Bridging Speech and Textual Pre-trained Models with Unsupervised ASR
Viaarxiv icon

Decoupling recognition and transcription in Mandarin ASR

Aug 02, 2021
Figure 1 for Decoupling recognition and transcription in Mandarin ASR
Figure 2 for Decoupling recognition and transcription in Mandarin ASR
Figure 3 for Decoupling recognition and transcription in Mandarin ASR
Figure 4 for Decoupling recognition and transcription in Mandarin ASR
Viaarxiv icon