Picture for Wilfried Michel

Wilfried Michel

End-to-End Training of a Neural HMM with Label and Transition Probabilities

Add code
Oct 09, 2023
Viaarxiv icon

Efficient Training of Neural Transducer for Speech Recognition

Add code
Apr 22, 2022
Figure 1 for Efficient Training of Neural Transducer for Speech Recognition
Figure 2 for Efficient Training of Neural Transducer for Speech Recognition
Figure 3 for Efficient Training of Neural Transducer for Speech Recognition
Figure 4 for Efficient Training of Neural Transducer for Speech Recognition
Viaarxiv icon

Conformer-based Hybrid ASR System for Switchboard Dataset

Add code
Nov 05, 2021
Figure 1 for Conformer-based Hybrid ASR System for Switchboard Dataset
Figure 2 for Conformer-based Hybrid ASR System for Switchboard Dataset
Figure 3 for Conformer-based Hybrid ASR System for Switchboard Dataset
Figure 4 for Conformer-based Hybrid ASR System for Switchboard Dataset
Viaarxiv icon

Automatic Learning of Subword Dependent Model Scales

Add code
Oct 18, 2021
Figure 1 for Automatic Learning of Subword Dependent Model Scales
Figure 2 for Automatic Learning of Subword Dependent Model Scales
Figure 3 for Automatic Learning of Subword Dependent Model Scales
Figure 4 for Automatic Learning of Subword Dependent Model Scales
Viaarxiv icon

Efficient Sequence Training of Attention Models using Approximative Recombination

Add code
Oct 18, 2021
Figure 1 for Efficient Sequence Training of Attention Models using Approximative Recombination
Figure 2 for Efficient Sequence Training of Attention Models using Approximative Recombination
Figure 3 for Efficient Sequence Training of Attention Models using Approximative Recombination
Figure 4 for Efficient Sequence Training of Attention Models using Approximative Recombination
Viaarxiv icon

Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models

Add code
Apr 12, 2021
Figure 1 for Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
Figure 2 for Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
Figure 3 for Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
Figure 4 for Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
Viaarxiv icon

Feature Replacement and Combination for Hybrid ASR Systems

Add code
Apr 09, 2021
Figure 1 for Feature Replacement and Combination for Hybrid ASR Systems
Figure 2 for Feature Replacement and Combination for Hybrid ASR Systems
Figure 3 for Feature Replacement and Combination for Hybrid ASR Systems
Figure 4 for Feature Replacement and Combination for Hybrid ASR Systems
Viaarxiv icon

Librispeech Transducer Model with Internal Language Model Prior Correction

Add code
Apr 07, 2021
Figure 1 for Librispeech Transducer Model with Internal Language Model Prior Correction
Figure 2 for Librispeech Transducer Model with Internal Language Model Prior Correction
Figure 3 for Librispeech Transducer Model with Internal Language Model Prior Correction
Figure 4 for Librispeech Transducer Model with Internal Language Model Prior Correction
Viaarxiv icon

Early Stage LM Integration Using Local and Global Log-Linear Combination

Add code
May 20, 2020
Figure 1 for Early Stage LM Integration Using Local and Global Log-Linear Combination
Figure 2 for Early Stage LM Integration Using Local and Global Log-Linear Combination
Figure 3 for Early Stage LM Integration Using Local and Global Log-Linear Combination
Figure 4 for Early Stage LM Integration Using Local and Global Log-Linear Combination
Viaarxiv icon

Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR

Add code
Jul 01, 2019
Figure 1 for Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
Figure 2 for Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
Figure 3 for Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
Figure 4 for Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
Viaarxiv icon