README.md

Speech recognition and speaker recognition algorithms

• This is a record of the learning of classical speech recognition and speaker recognition algorithms
• Welcome to my personal technology blog:https://www.cnblogs.com/zy230530/
• If you have any questions,please contact me.

Speech recognition algorithms

• CLDNN: CONVOLUTIONAL, LONG SHORT-TERM MEMORY,FULLY CONNECTED DEEP NEURAL NETWORKS,Google:https://www.cnblogs.com/zy230530/p/13658385.html
• CTC：Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks:https://www.cnblogs.com/zy230530/p/13661661.html
• listen, attented and spell,Google:https://www.cnblogs.com/zy230530/p/13661785.html
• RNNT:SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS,2013:https://www.cnblogs.com/zy230530/p/13675993.html
• EXPLORING ARCHITECTURES, DATA AND UNITS FOR STREAMING END-TO-END SPEECH RECOGNITION WITH RNN-TRANSDUCER,2018:https://www.cnblogs.com/zy230530/p/13676052.html
• EESEN:END-TO-END SPEECH RECOGNITION USING DEEP RNN MODELS AND WFST-BASED DECODING:https://www.cnblogs.com/zy230530/p/13676238.html
• IMPROVING LATENCY-CONTROLLED BLSTM ACOUSTIC MODELS FOR ONLINE SPEECH RECOGNITION:https://www.cnblogs.com/zy230530/p/13677580.html
• Feedforward Sequential Memory Networks:A New Structure to Learn Long-term Dependency:https://www.cnblogs.com/zy230530/p/13677721.html
• Compact Feedforward Sequential Memory Networks for Large Vocabulary Continuous Speech Recognition:https://www.cnblogs.com/zy230530/p/13677789.html
• Deep-FSMN for Large Vocabulary Continuous Speech Recognition:https://www.cnblogs.com/zy230530/p/13681669.html
• A NOVEL PYRAMIDAL-FSMN ARCHITECTURE WITH LATTICE-FREE MMI FOR SPEECH RECOGNITION:https://www.cnblogs.com/zy230530/p/13681722.html
• SPEECH-TRANSFORMER: A NO-RECURRENCE SEQUENCE-TO-SEQUENCE MODELFOR SPEECH RECOGNITION:https://www.cnblogs.com/zy230530/p/13681774.html
• THE SPEECHTRANSFORMER FOR LARGE-SCALE MANDARIN CHINESE SPEECH RECOGNITION:https://www.cnblogs.com/zy230530/p/13681892.html
• TRANSFORMER TRANSDUCER: A STREAMABLE SPEECH RECOGNITION MODELWITH TRANSFORMER ENCODERS AND RNN-T LOSS:https://www.cnblogs.com/zy230530/p/13681954.html
• TRANSFORMER-TRANSDUCER:END-TO-END SPEECH RECOGNITION WITH SELF-ATTENTION:https://www.cnblogs.com/zy230530/p/13682010.html
• A time delay neural network architecture for efficient modeling of longtemporal contexts:https://www.cnblogs.com/zy230530/p/13682126.html

speaker recognition algorithms

• VoxCeleb: a large-scale speaker identification dataset:https://www.cnblogs.com/zy230530/p/13657435.html
• VoxCeleb2: Deep Speaker Recognition:https://www.cnblogs.com/zy230530/p/13657462.html
• End-to-End Text-Dependent Speaker Verification:https://www.cnblogs.com/zy230530/p/13657502.html
• ATTENTION-BASED MODELS FOR TEXT-DEPENDENT SPEAKER VERIFICATION:https://www.cnblogs.com/zy230530/p/13657568.html
• GENERALIZED END-TO-END LOSS FOR SPEAKER VERIFICATION:https://www.cnblogs.com/zy230530/p/13657678.html
• Deep Speaker: an End-to-End Neural Speaker Embedding System:https://www.cnblogs.com/zy230530/p/13657717.html
• TEXT-INDEPENDENT SPEAKER VERIFICATION USING 3D CONVOLUTIONAL NEURAL NETWORKS:https://www.cnblogs.com/zy230530/p/13657771.html
• X-VECTORS: ROBUST DNN EMBEDDINGS FOR SPEAKER RECOGNITION:https://www.cnblogs.com/zy230530/p/13657793.html
• Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification:https://www.cnblogs.com/zy230530/p/13657823.html
• CN-Celeb: A CHALLENGING CHINESE SPEAKER RECOGNITION DATASET:https://www.cnblogs.com/zy230530/p/13715298.html

speech augment algorithms

• SpecAugment: A Simple Data Augmentation Methodfor Automatic Speech Recognition:https://www.cnblogs.com/zy230530/p/13682080.html