Picture for Ruizhi Li

Ruizhi Li

Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream End-to-End ASR

Feb 05, 2021
Figure 1 for Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream End-to-End ASR
Figure 2 for Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream End-to-End ASR
Figure 3 for Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream End-to-End ASR
Figure 4 for Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream End-to-End ASR
Viaarxiv icon

A practical two-stage training strategy for multi-stream end-to-end speech recognition

Oct 23, 2019
Figure 1 for A practical two-stage training strategy for multi-stream end-to-end speech recognition
Figure 2 for A practical two-stage training strategy for multi-stream end-to-end speech recognition
Figure 3 for A practical two-stage training strategy for multi-stream end-to-end speech recognition
Figure 4 for A practical two-stage training strategy for multi-stream end-to-end speech recognition
Viaarxiv icon

Multi-Stream End-to-End Speech Recognition

Jun 17, 2019
Figure 1 for Multi-Stream End-to-End Speech Recognition
Figure 2 for Multi-Stream End-to-End Speech Recognition
Figure 3 for Multi-Stream End-to-End Speech Recognition
Figure 4 for Multi-Stream End-to-End Speech Recognition
Viaarxiv icon

Performance Monitoring for End-to-End Speech Recognition

Apr 09, 2019
Figure 1 for Performance Monitoring for End-to-End Speech Recognition
Figure 2 for Performance Monitoring for End-to-End Speech Recognition
Figure 3 for Performance Monitoring for End-to-End Speech Recognition
Figure 4 for Performance Monitoring for End-to-End Speech Recognition
Viaarxiv icon

Exploring Methods for the Automatic Detection of Errors in Manual Transcription

Apr 08, 2019
Figure 1 for Exploring Methods for the Automatic Detection of Errors in Manual Transcription
Figure 2 for Exploring Methods for the Automatic Detection of Errors in Manual Transcription
Figure 3 for Exploring Methods for the Automatic Detection of Errors in Manual Transcription
Figure 4 for Exploring Methods for the Automatic Detection of Errors in Manual Transcription
Viaarxiv icon

Stream attention-based multi-array end-to-end speech recognition

Nov 12, 2018
Figure 1 for Stream attention-based multi-array end-to-end speech recognition
Figure 2 for Stream attention-based multi-array end-to-end speech recognition
Figure 3 for Stream attention-based multi-array end-to-end speech recognition
Figure 4 for Stream attention-based multi-array end-to-end speech recognition
Viaarxiv icon

Multi-encoder multi-resolution framework for end-to-end speech recognition

Nov 12, 2018
Figure 1 for Multi-encoder multi-resolution framework for end-to-end speech recognition
Figure 2 for Multi-encoder multi-resolution framework for end-to-end speech recognition
Figure 3 for Multi-encoder multi-resolution framework for end-to-end speech recognition
Figure 4 for Multi-encoder multi-resolution framework for end-to-end speech recognition
Viaarxiv icon

Large-scale Artificial Neural Network: MapReduce-based Deep Learning

Add code
Oct 09, 2015
Figure 1 for Large-scale Artificial Neural Network: MapReduce-based Deep Learning
Figure 2 for Large-scale Artificial Neural Network: MapReduce-based Deep Learning
Figure 3 for Large-scale Artificial Neural Network: MapReduce-based Deep Learning
Figure 4 for Large-scale Artificial Neural Network: MapReduce-based Deep Learning
Viaarxiv icon