Alert button

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

Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

Oct 28, 2019
Qiao Cheng, Meiyuan Fang, Yaqian Han, Jin Huang, Yitao Duan

Figure 1 for Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training
Figure 2 for Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training
Figure 3 for Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training
Figure 4 for Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training
Viaarxiv icon

Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech

Mar 21, 2022
Quan Wang, Yang Yu, Jason Pelecanos, Yiling Huang, Ignacio Lopez Moreno

Figure 1 for Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech
Figure 2 for Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech
Figure 3 for Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech
Figure 4 for Attentive Temporal Pooling for Conformer-based Streaming Language Identification in Long-form Speech
Viaarxiv icon

Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora

Apr 07, 2019
Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa

Figure 1 for Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Figure 2 for Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Figure 3 for Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Figure 4 for Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora
Viaarxiv icon

Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks

Oct 04, 2021
Zhaojie Luo, Shoufeng Lin, Rui Liu, Jun Baba, Yuichiro Yoshikawa, Ishiguro Hiroshi

Figure 1 for Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks
Figure 2 for Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks
Figure 3 for Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks
Figure 4 for Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks
Viaarxiv icon

Assessing Progress of Parkinson s Disease Using Acoustic Analysis of Phonation

Mar 17, 2022
Jiri Mekyska, Zoltan Galaz, Zdenek Mzourek, Zdenek Smekal, Irena Rektorova, Ilona Eliasova, Milena Kostalova, Martina Mrackova, Dagmar Berankov, Marcos Faundez-Zanuy, Karmele Lopez-de-Ipiña, Jesus B. Alonso-Hernandez

Figure 1 for Assessing Progress of Parkinson s Disease Using Acoustic Analysis of Phonation
Figure 2 for Assessing Progress of Parkinson s Disease Using Acoustic Analysis of Phonation
Figure 3 for Assessing Progress of Parkinson s Disease Using Acoustic Analysis of Phonation
Figure 4 for Assessing Progress of Parkinson s Disease Using Acoustic Analysis of Phonation
Viaarxiv icon

Noise-robust blind reverberation time estimation using noise-aware time-frequency masking

Dec 09, 2021
Kaitong Zheng, Chengshi Zheng, Jinqiu Sang, Yulong Zhang, Xiaodong Li

Figure 1 for Noise-robust blind reverberation time estimation using noise-aware time-frequency masking
Figure 2 for Noise-robust blind reverberation time estimation using noise-aware time-frequency masking
Figure 3 for Noise-robust blind reverberation time estimation using noise-aware time-frequency masking
Figure 4 for Noise-robust blind reverberation time estimation using noise-aware time-frequency masking
Viaarxiv icon

Automatic Fake News Detection: Are current models "fact-checking" or "gut-checking"?

Apr 14, 2022
Ian Kelk, Benjamin Basseri, Wee Yi Lee, Richard Qiu, Chris Tanner

Figure 1 for Automatic Fake News Detection: Are current models "fact-checking" or "gut-checking"?
Figure 2 for Automatic Fake News Detection: Are current models "fact-checking" or "gut-checking"?
Figure 3 for Automatic Fake News Detection: Are current models "fact-checking" or "gut-checking"?
Figure 4 for Automatic Fake News Detection: Are current models "fact-checking" or "gut-checking"?
Viaarxiv icon

Towards Building ASR Systems for the Next Billion Users

Nov 12, 2021
Tahir Javed, Sumanth Doddapaneni, Abhigyan Raman, Kaushal Santosh Bhogale, Gowtham Ramesh, Anoop Kunchukuttan, Pratyush Kumar, Mitesh M. Khapra

Figure 1 for Towards Building ASR Systems for the Next Billion Users
Figure 2 for Towards Building ASR Systems for the Next Billion Users
Figure 3 for Towards Building ASR Systems for the Next Billion Users
Figure 4 for Towards Building ASR Systems for the Next Billion Users
Viaarxiv icon

Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study

Aug 18, 2020
Karthik Gopalakrishnan, Behnam Hedayatnia, Longshaokan Wang, Yang Liu, Dilek Hakkani-Tur

Figure 1 for Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Figure 2 for Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Figure 3 for Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Figure 4 for Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Viaarxiv icon

End-to-end speaker diarization with transformer

Dec 14, 2021
Yongquan Lai, Xin Tang, Yuanyuan Fu, Rui Fang

Figure 1 for End-to-end speaker diarization with transformer
Figure 2 for End-to-end speaker diarization with transformer
Figure 3 for End-to-end speaker diarization with transformer
Figure 4 for End-to-end speaker diarization with transformer
Viaarxiv icon