Alert button

"speech recognition": models, code, and papers
Alert button

Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems

Sep 13, 2017
Yonatan Belinkov, James Glass

Figure 1 for Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
Figure 2 for Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
Figure 3 for Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
Figure 4 for Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
Viaarxiv icon

Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Switchboard Corpus

Jun 23, 2022
Junhao Xu, Shoukang Hu, Xunying Liu, Helen Meng

Figure 1 for Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Switchboard Corpus
Figure 2 for Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Switchboard Corpus
Viaarxiv icon

Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems

Jun 23, 2022
Mingyu Cui, Jiajun Deng, Shoukang Hu, Xurong Xie, Tianzi Wang, Shujie Hu, Mengzhe Geng, Boyang Xue, Xunying Liu, Helen Meng

Figure 1 for Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems
Figure 2 for Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems
Figure 3 for Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems
Figure 4 for Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems
Viaarxiv icon

Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities

Dec 14, 2019
Khe Chai Sim, Françoise Beaufays, Arnaud Benard, Dhruv Guliani, Andreas Kabel, Nikhil Khare, Tamar Lucassen, Petr Zadrazil, Harry Zhang, Leif Johnson, Giovanni Motta, Lillian Zhou

Figure 1 for Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
Figure 2 for Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
Figure 3 for Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
Figure 4 for Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities
Viaarxiv icon

Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition

Feb 19, 2020
Shuai Zhang, Jiangyan Yi, Zhengkun Tian, Jianhua Tao, Ye Bai

Figure 1 for Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
Figure 2 for Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
Figure 3 for Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
Figure 4 for Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
Viaarxiv icon

Training Neural Networks using SAT solvers

Jun 10, 2022
Subham S. Sahoo

Figure 1 for Training Neural Networks using SAT solvers
Figure 2 for Training Neural Networks using SAT solvers
Figure 3 for Training Neural Networks using SAT solvers
Viaarxiv icon

A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement

Jun 22, 2022
Or Tal, Moshe Mandel, Felix Kreuk, Yossi Adi

Figure 1 for A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement
Figure 2 for A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement
Figure 3 for A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement
Figure 4 for A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement
Viaarxiv icon

Joint Speech Recognition and Speaker Diarization via Sequence Transduction

Jul 09, 2019
Laurent El Shafey, Hagen Soltau, Izhak Shafran

Figure 1 for Joint Speech Recognition and Speaker Diarization via Sequence Transduction
Figure 2 for Joint Speech Recognition and Speaker Diarization via Sequence Transduction
Figure 3 for Joint Speech Recognition and Speaker Diarization via Sequence Transduction
Figure 4 for Joint Speech Recognition and Speaker Diarization via Sequence Transduction
Viaarxiv icon

Continuous Metric Learning For Transferable Speech Emotion Recognition and Embedding Across Low-resource Languages

Mar 28, 2022
Sneha Das, Nicklas Leander Lund, Nicole Nadine Lønfeldt, Anne Katrine Pagsberg, Line H. Clemmensen

Figure 1 for Continuous Metric Learning For Transferable Speech Emotion Recognition and Embedding Across Low-resource Languages
Figure 2 for Continuous Metric Learning For Transferable Speech Emotion Recognition and Embedding Across Low-resource Languages
Figure 3 for Continuous Metric Learning For Transferable Speech Emotion Recognition and Embedding Across Low-resource Languages
Figure 4 for Continuous Metric Learning For Transferable Speech Emotion Recognition and Embedding Across Low-resource Languages
Viaarxiv icon

Cross Lingual Cross Corpus Speech Emotion Recognition

Mar 18, 2020
Shivali Goel, Homayoon Beigi

Figure 1 for Cross Lingual Cross Corpus Speech Emotion Recognition
Figure 2 for Cross Lingual Cross Corpus Speech Emotion Recognition
Figure 3 for Cross Lingual Cross Corpus Speech Emotion Recognition
Figure 4 for Cross Lingual Cross Corpus Speech Emotion Recognition
Viaarxiv icon