Alert button

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

TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices

Aug 16, 2020
Alexander Wong, Mahmoud Famouri, Maya Pavlova, Siddharth Surana

Figure 1 for TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
Figure 2 for TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
Figure 3 for TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
Viaarxiv icon

Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End

May 14, 2021
Swayambhu Nath Ray, Minhua Wu, Anirudh Raju, Pegah Ghahremani, Raghavendra Bilgi, Milind Rao, Harish Arsikere, Ariya Rastrow, Andreas Stolcke, Jasha Droppo

Figure 1 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Figure 2 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Figure 3 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Figure 4 for Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Viaarxiv icon

Evolutionary optimization of contexts for phonetic correction in speech recognition systems

Feb 23, 2021
Rafael Viana-Cámara, Diego Campos-Sobrino, Mario Campos-Soberanis

Figure 1 for Evolutionary optimization of contexts for phonetic correction in speech recognition systems
Figure 2 for Evolutionary optimization of contexts for phonetic correction in speech recognition systems
Figure 3 for Evolutionary optimization of contexts for phonetic correction in speech recognition systems
Figure 4 for Evolutionary optimization of contexts for phonetic correction in speech recognition systems
Viaarxiv icon

Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding

Oct 05, 2020
Yu-An Chung, Chenguang Zhu, Michael Zeng

Figure 1 for Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding
Figure 2 for Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding
Figure 3 for Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding
Figure 4 for Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding
Viaarxiv icon

An Online Multilingual Hate speech Recognition System

Dec 22, 2020
Neeraj Vashistha, Arkaitz Zubiaga, Shanky Sharma

Figure 1 for An Online Multilingual Hate speech Recognition System
Figure 2 for An Online Multilingual Hate speech Recognition System
Figure 3 for An Online Multilingual Hate speech Recognition System
Figure 4 for An Online Multilingual Hate speech Recognition System
Viaarxiv icon

Utterance-by-utterance overlap-aware neural diarization with Graph-PIT

Jul 28, 2022
Keisuke Kinoshita, Thilo von Neumann, Marc Delcroix, Christoph Boeddeker, Reinhold Haeb-Umbach

Figure 1 for Utterance-by-utterance overlap-aware neural diarization with Graph-PIT
Figure 2 for Utterance-by-utterance overlap-aware neural diarization with Graph-PIT
Viaarxiv icon

Complex Spectral Mapping With Attention Based Convolution Recrrent Neural Network for Speech Enhancement

Apr 12, 2021
Liming Zhou, Yongyu Gao, Ziluo Wang, Jiwei Li, Wenbin Zhang

Figure 1 for Complex Spectral Mapping With Attention Based Convolution Recrrent Neural Network for Speech Enhancement
Figure 2 for Complex Spectral Mapping With Attention Based Convolution Recrrent Neural Network for Speech Enhancement
Figure 3 for Complex Spectral Mapping With Attention Based Convolution Recrrent Neural Network for Speech Enhancement
Figure 4 for Complex Spectral Mapping With Attention Based Convolution Recrrent Neural Network for Speech Enhancement
Viaarxiv icon

Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition

Aug 09, 2021
Arash Dehghani, Seyyed Ali Seyyedsalehi

Figure 1 for Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition
Figure 2 for Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition
Figure 3 for Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition
Figure 4 for Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition
Viaarxiv icon

Are Chess Discussions Racist? An Adversarial Hate Speech Data Set

Nov 20, 2020
Rupak Sarkar, Ashiqur R. KhudaBukhsh

Figure 1 for Are Chess Discussions Racist? An Adversarial Hate Speech Data Set
Figure 2 for Are Chess Discussions Racist? An Adversarial Hate Speech Data Set
Figure 3 for Are Chess Discussions Racist? An Adversarial Hate Speech Data Set
Viaarxiv icon

Cyclic Defense GAN Against Speech Adversarial Attacks

Mar 26, 2021
Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich

Figure 1 for Cyclic Defense GAN Against Speech Adversarial Attacks
Figure 2 for Cyclic Defense GAN Against Speech Adversarial Attacks
Viaarxiv icon