Alert button
Picture for Yossi Adi

Yossi Adi

Alert button

Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation

Apr 06, 2022
Sravya Popuri, Peng-Jen Chen, Changhan Wang, Juan Pino, Yossi Adi, Jiatao Gu, Wei-Ning Hsu, Ann Lee

Figure 1 for Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
Figure 2 for Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
Figure 3 for Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
Figure 4 for Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
Viaarxiv icon

Generative Spoken Dialogue Language Modeling

Mar 30, 2022
Tu Anh Nguyen, Eugene Kharitonov, Jade Copet, Yossi Adi, Wei-Ning Hsu, Ali Elkahky, Paden Tomasello, Robin Algayres, Benoit Sagot, Abdelrahman Mohamed, Emmanuel Dupoux

Figure 1 for Generative Spoken Dialogue Language Modeling
Figure 2 for Generative Spoken Dialogue Language Modeling
Figure 3 for Generative Spoken Dialogue Language Modeling
Figure 4 for Generative Spoken Dialogue Language Modeling
Viaarxiv icon

Probing phoneme, language and speaker information in unsupervised speech representations

Mar 30, 2022
Maureen de Seyssel, Marvin Lavechin, Yossi Adi, Emmanuel Dupoux, Guillaume Wisniewski

Figure 1 for Probing phoneme, language and speaker information in unsupervised speech representations
Figure 2 for Probing phoneme, language and speaker information in unsupervised speech representations
Figure 3 for Probing phoneme, language and speaker information in unsupervised speech representations
Figure 4 for Probing phoneme, language and speaker information in unsupervised speech representations
Viaarxiv icon

RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing

Feb 22, 2022
Efthymios Tzinis, Yossi Adi, Vamsi Krishna Ithapu, Buye Xu, Paris Smaragdis, Anurag Kumar

Figure 1 for RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
Figure 2 for RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
Figure 3 for RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
Figure 4 for RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
Viaarxiv icon

textless-lib: a Library for Textless Spoken Language Processing

Feb 15, 2022
Eugene Kharitonov, Jade Copet, Kushal Lakhotia, Tu Anh Nguyen, Paden Tomasello, Ann Lee, Ali Elkahky, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux, Yossi Adi

Figure 1 for textless-lib: a Library for Textless Spoken Language Processing
Figure 2 for textless-lib: a Library for Textless Spoken Language Processing
Figure 3 for textless-lib: a Library for Textless Spoken Language Processing
Figure 4 for textless-lib: a Library for Textless Spoken Language Processing
Viaarxiv icon

Textless Speech Emotion Conversion using Decomposed and Discrete Representations

Nov 14, 2021
Felix Kreuk, Adam Polyak, Jade Copet, Eugene Kharitonov, Tu-Anh Nguyen, Morgane Rivière, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux, Yossi Adi

Figure 1 for Textless Speech Emotion Conversion using Decomposed and Discrete Representations
Figure 2 for Textless Speech Emotion Conversion using Decomposed and Discrete Representations
Figure 3 for Textless Speech Emotion Conversion using Decomposed and Discrete Representations
Figure 4 for Textless Speech Emotion Conversion using Decomposed and Discrete Representations
Viaarxiv icon

Continual self-training with bootstrapped remixing for speech enhancement

Oct 19, 2021
Efthymios Tzinis, Yossi Adi, Vamsi K. Ithapu, Buye Xu, Anurag Kumar

Figure 1 for Continual self-training with bootstrapped remixing for speech enhancement
Figure 2 for Continual self-training with bootstrapped remixing for speech enhancement
Figure 3 for Continual self-training with bootstrapped remixing for speech enhancement
Viaarxiv icon

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

Sep 14, 2021
Changhan Wang, Wei-Ning Hsu, Yossi Adi, Adam Polyak, Ann Lee, Peng-Jen Chen, Jiatao Gu, Juan Pino

Figure 1 for fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
Figure 2 for fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
Figure 3 for fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
Figure 4 for fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
Viaarxiv icon

Text-Free Prosody-Aware Generative Spoken Language Modeling

Sep 07, 2021
Eugene Kharitonov, Ann Lee, Adam Polyak, Yossi Adi, Jade Copet, Kushal Lakhotia, Tu-Anh Nguyen, Morgane Rivière, Abdelrahman Mohamed, Emmanuel Dupoux, Wei-Ning Hsu

Figure 1 for Text-Free Prosody-Aware Generative Spoken Language Modeling
Figure 2 for Text-Free Prosody-Aware Generative Spoken Language Modeling
Figure 3 for Text-Free Prosody-Aware Generative Spoken Language Modeling
Figure 4 for Text-Free Prosody-Aware Generative Spoken Language Modeling
Viaarxiv icon

Online Self-Attentive Gated RNNs for Real-Time Speaker Separation

Jul 27, 2021
Ori Kabeli, Yossi Adi, Zhenyu Tang, Buye Xu, Anurag Kumar

Figure 1 for Online Self-Attentive Gated RNNs for Real-Time Speaker Separation
Figure 2 for Online Self-Attentive Gated RNNs for Real-Time Speaker Separation
Figure 3 for Online Self-Attentive Gated RNNs for Real-Time Speaker Separation
Figure 4 for Online Self-Attentive Gated RNNs for Real-Time Speaker Separation
Viaarxiv icon