Picture for Maarten Van Segbroeck

Maarten Van Segbroeck

Personalized Predictive ASR for Latency Reduction in Voice Assistants

Add code
May 23, 2023
Viaarxiv icon

Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition

Add code
Jul 27, 2020
Figure 1 for Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition
Figure 2 for Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition
Figure 3 for Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition
Figure 4 for Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition
Viaarxiv icon

Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition

Add code
Jun 30, 2020
Viaarxiv icon

DiPCo -- Dinner Party Corpus

Add code
Sep 30, 2019
Figure 1 for DiPCo -- Dinner Party Corpus
Figure 2 for DiPCo -- Dinner Party Corpus
Figure 3 for DiPCo -- Dinner Party Corpus
Figure 4 for DiPCo -- Dinner Party Corpus
Viaarxiv icon