Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error von McDermott, E., Hazen, T.J., Le Roux, J., Nakamura, A., Katagiri, S.

Volltext

Deep clustering-based single-channel speech separation and recent advances von Aihara, Ryo, Wichern, Gordon, Roux, Jonathan Le

Volltext

Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation von Wang, Zhong-Qiu, Wichern, Gordon, Roux, Jonathan Le

Volltext

Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks von Petermann, Darius, Wichern, Gordon, Subramanian, Aswin Shanmugam, Wang, Zhong-Qiu, Roux, Jonathan Le

Volltext

The Sound Demixing Challenge 2023 – Cinematic Demixing Track von Uhlich, Stefan, Fabbro, Giorgio, Hirano, Masato, Takahashi, Shusuke, Wichern, Gordon, Le Roux, Jonathan, Chakraborty, Dipam, Mohanty, Sharada, Li, Kai, Luo, Yi, Yu, Jianwei, Gu, Rongzhi, Solovyev, Roman, Stempkovskiy, Alexander, Habruseva, Tatiana, Sukhovei, Mikhail, Mitsufuji, Yuki

Volltext

On the Compensation Between Magnitude and Phase in Speech Separation von Wang, Zhong-Qiu, Wichern, Gordon, Le Roux, Jonathan

Volltext

Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision von Pishdadian, Fatemeh, Wichern, Gordon, Le Roux, Jonathan

Volltext

Momentum Pseudo-Labeling: Semi-Supervised ASR With Continuously Improving Pseudo-Labels von Higuchi, Yosuke, Moritz, Niko, Le Roux, Jonathan, Hori, Takaaki

Volltext

STFT-Domain Neural Speech Enhancement With Very Low Algorithmic Latency von Wang, Zhong-Qiu, Wichern, Gordon, Watanabe, Shinji, Le Roux, Jonathan

Volltext

Duration-Controlled LSTM for Polyphonic Sound Event Detection von Hayashi, Tomoki, Watanabe, Shinji, Toda, Tomoki, Hori, Takaaki, Le Roux, Jonathan, Takeda, Kazuya

Volltext

TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings von Boeddeker, Christoph, Subramanian, Aswin Shanmugam, Wichern, Gordon, Haeb-Umbach, Reinhold, Le Roux, Jonathan

Volltext

Phasebook and Friends: Leveraging Discrete Representations for Source Separation von Le Roux, Jonathan, Wichern, Gordon, Watanabe, Shinji, Sarroff, Andy, Hershey, John R.

Volltext

Bayesian nonparametric spectrogram modeling based on infinite factorial infinite hidden Markov model von Nakano, M., Le Roux, J., Kameoka, H., Nakamura, T., Ono, N., Sagayama, S.

Volltext

Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones von Tachioka, Yuuki, Watanabe, Shinji, Roux, Jonathan Le, Hershey, John R.

Volltext

Latent Iterative Refinement for Modular Source Separation von Bralios, Dimitrios, Tzinis, Efthymios, Wichern, Gordon, Paris Smaragdis, Jonathan Le Roux

Volltext

Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR von Weninger, Felix, Erdogan, Hakan, Watanabe, Shinji, Vincent, Emmanuel, Le Roux, Jonathan, Hershey, John R., Schuller, Björn

Volltext

Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision von Pishdadian, Fatemeh, Wichern, Gordon, Jonathan Le Roux

Volltext

Heterogeneous Target Speech Separation von Tzinis, Efthymios, Wichern, Gordon, Subramanian, Aswin, Paris Smaragdis, Jonathan Le Roux

Volltext

Consistent Wiener Filtering for Audio Source Separation von Le Roux, J., Vincent, E.

Volltext

On The Compensation Between Magnitude and Phase in Speech Separation von Zhong-Qiu, Wang, Wichern, Gordon, Jonathan Le Roux

Volltext