Picture for Catalin Zorila

Catalin Zorila

Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition

Apr 24, 2023
Figure 1 for Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition
Figure 2 for Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition
Figure 3 for Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition
Figure 4 for Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition
Viaarxiv icon

Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition

Add code
May 09, 2022
Figure 1 for Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition
Figure 2 for Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition
Figure 3 for Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition
Figure 4 for Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition
Viaarxiv icon

On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training

Add code
May 03, 2022
Figure 1 for On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
Figure 2 for On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
Figure 3 for On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
Figure 4 for On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
Viaarxiv icon

Transformer-based Streaming ASR with Cumulative Attention

Mar 11, 2022
Figure 1 for Transformer-based Streaming ASR with Cumulative Attention
Figure 2 for Transformer-based Streaming ASR with Cumulative Attention
Figure 3 for Transformer-based Streaming ASR with Cumulative Attention
Figure 4 for Transformer-based Streaming ASR with Cumulative Attention
Viaarxiv icon

Monaural source separation: From anechoic to reverberant environments

Nov 15, 2021
Figure 1 for Monaural source separation: From anechoic to reverberant environments
Figure 2 for Monaural source separation: From anechoic to reverberant environments
Figure 3 for Monaural source separation: From anechoic to reverberant environments
Figure 4 for Monaural source separation: From anechoic to reverberant environments
Viaarxiv icon

Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation

Jun 16, 2021
Figure 1 for Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
Figure 2 for Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
Figure 3 for Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
Figure 4 for Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation
Viaarxiv icon

Head-synchronous Decoding for Transformer-based Streaming ASR

Apr 26, 2021
Figure 1 for Head-synchronous Decoding for Transformer-based Streaming ASR
Figure 2 for Head-synchronous Decoding for Transformer-based Streaming ASR
Figure 3 for Head-synchronous Decoding for Transformer-based Streaming ASR
Figure 4 for Head-synchronous Decoding for Transformer-based Streaming ASR
Viaarxiv icon

Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism

Feb 07, 2021
Figure 1 for Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
Figure 2 for Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
Figure 3 for Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
Figure 4 for Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism
Viaarxiv icon

On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments

Nov 11, 2020
Figure 1 for On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments
Figure 2 for On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments
Figure 3 for On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments
Figure 4 for On End-to-end Multi-channel Time Domain Speech Separation in Reverberant Environments
Viaarxiv icon

An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription

Add code
Sep 26, 2019
Figure 1 for An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription
Figure 2 for An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription
Figure 3 for An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription
Figure 4 for An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription
Viaarxiv icon