Picture for Nauman Dawalatabad

Nauman Dawalatabad

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

Add code
Jun 01, 2023
Figure 1 for Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
Figure 2 for Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
Figure 3 for Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
Figure 4 for Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
Viaarxiv icon

On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration

Nov 14, 2022
Figure 1 for On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration
Figure 2 for On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration
Figure 3 for On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration
Figure 4 for On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration
Viaarxiv icon

Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition

Oct 01, 2022
Figure 1 for Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition
Figure 2 for Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition
Figure 3 for Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition
Figure 4 for Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition
Viaarxiv icon

Two-Pass End-to-End ASR Model Compression

Jan 08, 2022
Figure 1 for Two-Pass End-to-End ASR Model Compression
Figure 2 for Two-Pass End-to-End ASR Model Compression
Figure 3 for Two-Pass End-to-End ASR Model Compression
Figure 4 for Two-Pass End-to-End ASR Model Compression
Viaarxiv icon

SpeechBrain: A General-Purpose Speech Toolkit

Add code
Jun 08, 2021
Figure 1 for SpeechBrain: A General-Purpose Speech Toolkit
Figure 2 for SpeechBrain: A General-Purpose Speech Toolkit
Figure 3 for SpeechBrain: A General-Purpose Speech Toolkit
Figure 4 for SpeechBrain: A General-Purpose Speech Toolkit
Viaarxiv icon

ECAPA-TDNN Embeddings for Speaker Diarization

Add code
Apr 03, 2021
Figure 1 for ECAPA-TDNN Embeddings for Speaker Diarization
Figure 2 for ECAPA-TDNN Embeddings for Speaker Diarization
Figure 3 for ECAPA-TDNN Embeddings for Speaker Diarization
Figure 4 for ECAPA-TDNN Embeddings for Speaker Diarization
Viaarxiv icon

Front-end Diarization for Percussion Separation in Taniavartanam of Carnatic Music Concerts

Add code
Mar 04, 2021
Figure 1 for Front-end Diarization for Percussion Separation in Taniavartanam of Carnatic Music Concerts
Figure 2 for Front-end Diarization for Percussion Separation in Taniavartanam of Carnatic Music Concerts
Figure 3 for Front-end Diarization for Percussion Separation in Taniavartanam of Carnatic Music Concerts
Figure 4 for Front-end Diarization for Percussion Separation in Taniavartanam of Carnatic Music Concerts
Viaarxiv icon