Picture for Mingyu Cui

Mingyu Cui

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement

Add code
Jun 17, 2024
Viaarxiv icon

Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask

Add code
Jun 14, 2024
Figure 1 for Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
Figure 2 for Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
Figure 3 for Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
Figure 4 for Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
Viaarxiv icon

One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model

Add code
Jun 14, 2024
Figure 1 for One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
Figure 2 for One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
Figure 3 for One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
Figure 4 for One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model
Viaarxiv icon

Cross-Speaker Encoding Network for Multi-Talker Speech Recognition

Add code
Jan 08, 2024
Figure 1 for Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
Figure 2 for Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
Figure 3 for Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
Figure 4 for Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
Viaarxiv icon

Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition

Add code
Jul 06, 2023
Figure 1 for Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition
Figure 2 for Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition
Figure 3 for Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition
Figure 4 for Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition
Viaarxiv icon

Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems

Add code
Jun 26, 2023
Figure 1 for Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems
Figure 2 for Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems
Figure 3 for Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems
Figure 4 for Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems
Viaarxiv icon

Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems

Add code
Jun 26, 2023
Figure 1 for Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems
Figure 2 for Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems
Figure 3 for Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems
Figure 4 for Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems
Viaarxiv icon

Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator

Add code
May 25, 2023
Figure 1 for Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator
Figure 2 for Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator
Figure 3 for Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator
Figure 4 for Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator
Viaarxiv icon

Use of Speech Impairment Severity for Dysarthric Speech Recognition

Add code
May 18, 2023
Figure 1 for Use of Speech Impairment Severity for Dysarthric Speech Recognition
Figure 2 for Use of Speech Impairment Severity for Dysarthric Speech Recognition
Figure 3 for Use of Speech Impairment Severity for Dysarthric Speech Recognition
Figure 4 for Use of Speech Impairment Severity for Dysarthric Speech Recognition
Viaarxiv icon

A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One

Add code
Mar 05, 2023
Figure 1 for A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One
Figure 2 for A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One
Figure 3 for A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One
Figure 4 for A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One
Viaarxiv icon