Jonathan Le Roux

Jonathan Le Roux
  • Biography

    Jonathan completed his B.Sc. and M.Sc. in Mathematics at the École Normale Supérieure in Paris, France. Before joining MERL in 2011, he spent several years in Beijing and Tokyo. In Tokyo he worked as a postdoctoral researcher at NTT's Communication Science Laboratories. His research interests are in signal processing and machine learning applied to speech and audio.

  • Recent News & Events

    •  NEWS    Jonathan Le Roux gives invited talk at CMU's Language Technology Institute Colloquium
      Date: December 9, 2022
      Where: Pittsburg, PA
      MERL Contact: Jonathan Le Roux
      Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
      Brief
      • MERL Senior Principal Research Scientist and Speech and Audio Senior Team Leader, Jonathan Le Roux, was invited by Carnegie Mellon University's Language Technology Institute (LTI) to give an invited talk as part of the LTI Colloquium Series. The LTI Colloquium is a prestigious series of talks given by experts from across the country related to different areas of language technologies. Jonathan's talk, entitled "Towards general and flexible audio source separation", presented an overview of techniques developed at MERL towards the goal of robustly and flexibly decomposing and analyzing an acoustic scene, describing in particular the Speech and Audio Team's efforts to extend MERL's early speech separation and enhancement methods to more challenging environments, and to more general and less supervised scenarios.
    •  
    •  EVENT    SANE 2022 - Speech and Audio in the Northeast
      Date: Thursday, October 6, 2022
      Location: Kendall Square, Cambridge, MA
      MERL Contacts: Anoop Cherian; Jonathan Le Roux
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
      Brief
      • SANE 2022, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, was held on Thursday October 6, 2022 in Kendall Square, Cambridge, MA.

        It was the 9th edition in the SANE series of workshops, which started in 2012 and was held every year alternately in Boston and New York until 2019. Since the first edition, the audience has grown to a record 200 participants and 45 posters in 2019. After a 2-year hiatus due to the pandemic, SANE returned with an in-person gathering of 140 students and researchers.

        SANE 2022 featured invited talks by seven leading researchers from the Northeast: Rupal Patel (Northeastern/VocaliD), Wei-Ning Hsu (Meta FAIR), Scott Wisdom (Google), Tara Sainath (Google), Shinji Watanabe (CMU), Anoop Cherian (MERL), and Chuang Gan (UMass Amherst/MIT-IBM Watson AI Lab). It also featured a lively poster session with 29 posters.

        SANE 2022 was co-organized by Jonathan Le Roux (MERL), Arnab Ghoshal (Apple), John Hershey (Google), and Shinji Watanabe (CMU). SANE remained a free event thanks to generous sponsorship by Bose, Google, MERL, and Microsoft.

        Slides and videos of the talks will be released on the SANE workshop website.
    •  

    See All News & Events for Jonathan
  • Awards

    •  AWARD    Best Poster Award and Best Video Award at the International Society for Music Information Retrieval Conference (ISMIR) 2020
      Date: October 15, 2020
      Awarded to: Ethan Manilow, Gordon Wichern, Jonathan Le Roux
      MERL Contacts: Jonathan Le Roux; Gordon Wichern
      Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
      Brief
      • Former MERL intern Ethan Manilow and MERL researchers Gordon Wichern and Jonathan Le Roux won Best Poster Award and Best Video Award at the 2020 International Society for Music Information Retrieval Conference (ISMIR 2020) for the paper "Hierarchical Musical Source Separation". The conference was held October 11-14 in a virtual format. The Best Poster Awards and Best Video Awards were awarded by popular vote among the conference attendees.

        The paper proposes a new method for isolating individual sounds in an audio mixture that accounts for the hierarchical relationship between sound sources. Many sounds we are interested in analyzing are hierarchical in nature, e.g., during a music performance, a hi-hat note is one of many such hi-hat notes, which is one of several parts of a drumkit, itself one of many instruments in a band, which might be playing in a bar with other sounds occurring. Inspired by this, the paper re-frames the audio source separation problem as hierarchical, combining similar sounds together at certain levels while separating them at other levels, and shows on a musical instrument separation task that a hierarchical approach outperforms non-hierarchical models while also requiring less training data. The paper, poster, and video can be seen on the paper page on the ISMIR website.
    •  
    •  AWARD    Best Paper Award at the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2019
      Date: December 18, 2019
      Awarded to: Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe
      MERL Contact: Jonathan Le Roux
      Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
      Brief
      • MERL researcher Jonathan Le Roux and co-authors Xuankai Chang, Shinji Watanabe (Johns Hopkins University), Wangyou Zhang, and Yanmin Qian (Shanghai Jiao Tong University) won the Best Paper Award at the 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2019), for the paper "MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition". MIMO-Speech is a fully neural end-to-end framework that can transcribe the text of multiple speakers speaking simultaneously from multi-channel input. The system is comprised of a monaural masking network, a multi-source neural beamformer, and a multi-output speech recognition model, which are jointly optimized only via an automatic speech recognition (ASR) criterion. The award was received by lead author Xuankai Chang during the conference, which was held in Sentosa, Singapore from December 14-18, 2019.
    •  
    •  AWARD    Best Student Paper Award at IEEE ICASSP 2018
      Date: April 17, 2018
      Awarded to: Zhong-Qiu Wang
      MERL Contact: Jonathan Le Roux
      Research Area: Speech & Audio
      Brief
      • Former MERL intern Zhong-Qiu Wang (Ph.D. Candidate at Ohio State University) has received a Best Student Paper Award at the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018) for the paper "Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation" by Zhong-Qiu Wang, Jonathan Le Roux, and John Hershey. The paper presents work performed during Zhong-Qiu's internship at MERL in the summer 2017, extending MERL's pioneering Deep Clustering framework for speech separation to a multi-channel setup. The award was received on behalf on Zhong-Qiu by MERL researcher and co-author Jonathan Le Roux during the conference, held in Calgary April 15-20.
    •  
    •  AWARD    MERL's Speech Team Achieves World's 2nd Best Performance at the Third CHiME Speech Separation and Recognition Challenge
      Date: December 15, 2015
      Awarded to: John R. Hershey, Takaaki Hori, Jonathan Le Roux and Shinji Watanabe
      MERL Contact: Jonathan Le Roux
      Research Area: Speech & Audio
      Brief
      • The results of the third 'CHiME' Speech Separation and Recognition Challenge were publicly announced on December 15 at the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015) held in Scottsdale, Arizona, USA. MERL's Speech and Audio Team, in collaboration with SRI, ranked 2nd out of 26 teams from Europe, Asia and the US. The task this year was to recognize speech recorded using a tablet in real environments such as cafes, buses, or busy streets. Due to the high levels of noise and the distance from the speaker's mouth to the microphones, this is very challenging task, where the baseline system only achieved 33.4% word error rate. The MERL/SRI system featured state-of-the-art techniques including multi-channel front-end, noise-robust feature extraction, and deep learning for speech enhancement, acoustic modeling, and language modeling, leading to a dramatic 73% reduction in word error rate, down to 9.1%. The core of the system has since been released as a new official challenge baseline for the community to use.
    •  
    •  AWARD    Awaya Prize Young Researcher Award
      Date: March 11, 2014
      Awarded to: Yuuki Tachioka
      Awarded for: "Effectiveness of discriminative approaches for speech recognition under noisy environments on the 2nd CHiME Challenge"
      Awarded by: Acoustical Society of Japan (ASJ)
      MERL Contact: Jonathan Le Roux
      Research Area: Speech & Audio
      Brief
      • MELCO researcher Yuuki Tachioka received the Awaya Prize Young Researcher Award from the Acoustical Society of Japan (ASJ) for "effectiveness of discriminative approaches for speech recognition under noisy environments on the 2nd CHiME Challenge", which was based on joint work with MERL Speech & Audio team researchers Shinji Watanabe, Jonathan Le Roux and John R. Hershey.
    •  
    •  AWARD    Awaya Prize Young Researcher Award
      Date: September 26, 2013
      Awarded to: Jonathan Le Roux
      Awarded for: "A new non-negative dynamical system for speech and audio modeling"
      Awarded by: Acoustical Society of Japan (ASJ)
      MERL Contact: Jonathan Le Roux
      Research Area: Speech & Audio
    •  
    •  AWARD    CHiME 2012 Speech Separation and Recognition Challenge Best Performance
      Date: June 1, 2013
      Awarded to: Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux and John R. Hershey
      Awarded for: "Discriminative Methods for Noise Robust Speech Recognition: A CHiME Challenge Benchmark"
      Awarded by: International Workshop on Machine Listening in Multisource Environments (CHiME)
      MERL Contact: Jonathan Le Roux
      Research Area: Speech & Audio
      Brief
      • The results of the 2nd 'CHiME' Speech Separation and Recognition Challenge are out! The team formed by MELCO researcher Yuuki Tachioka and MERL Speech & Audio team researchers Shinji Watanabe, Jonathan Le Roux and John Hershey obtained the best results in the continuous speech recognition task (Track 2). This very challenging task consisted in recognizing speech corrupted by highly non-stationary noises recorded in a real living room. Our proposal, which also included a simple yet extremely efficient denoising front-end, focused on investigating and developing state-of-the-art automatic speech recognition back-end techniques: feature transformation methods, as well as discriminative training methods for acoustic and language modeling. Our system significantly outperformed other participants. Our code has since been released as an improved baseline for the community to use.
    •  
    See All Awards for MERL
  • Research Highlights

  • MERL Publications

    •  Boeddeker, C., Subramanian, A.S., Wichern, G., Haeb-Umbach, R., Le Roux, J., "TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings", arXiv, March 2023.
      BibTeX arXiv
      • @article{Boeddeker2023mar,
      • author = {Boeddeker, Christoph and Subramanian, Aswin Shanmugam and Wichern, Gordon and Haeb-Umbach, Reinhold and Le Roux, Jonathan},
      • title = {TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings},
      • journal = {arXiv},
      • year = 2023,
      • month = mar,
      • url = {https://arxiv.org/abs/2303.03849}
      • }
    •  Petermann, D., Wichern, G., Subramanian, A.S., Wang, Z.-Q., Le Roux, J., "Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks", arXiv, December 2022.
      BibTeX arXiv
      • @article{Petermann2022dec2,
      • author = {Petermann, Darius and Wichern, Gordon and Subramanian, Aswin Shanmugam and Wang, Zhong-Qiu and Le Roux, Jonathan},
      • title = {Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks},
      • journal = {arXiv},
      • year = 2022,
      • month = dec,
      • url = {https://arxiv.org/abs/2212.07327}
      • }
    •  Wang, Z.-Q., Wichern, G., Watanabe, S., Le Roux, J., "STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency", IEEE/ACM Transactions on Audio, Speech, and Language Processing, December 2022.
      BibTeX TR2022-166 PDF
      • @article{Wang2022dec2,
      • author = {Wang, Zhong-Qiu and Wichern, Gordon and Watanabe, Shinji and Le Roux, Jonathan},
      • title = {STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency},
      • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
      • year = 2022,
      • month = dec,
      • url = {https://www.merl.com/publications/TR2022-166}
      • }
    •  Petermann, D., Wichern, G., Subramanian, A.S., Le Roux, J., "Hyperbolic Audio Source Separation", arXiv, December 2022.
      BibTeX arXiv
      • @article{Petermann2022dec,
      • author = {Petermann, Darius and Wichern, Gordon and Subramanian, Aswin Shanmugam and Le Roux, Jonathan},
      • title = {Hyperbolic Audio Source Separation},
      • journal = {arXiv},
      • year = 2022,
      • month = dec,
      • url = {https://arxiv.org/abs/2212.05008}
      • }
    •  Bralios, D., Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Latent Iterative Refinement for Modular Source Separation", arXiv, November 2022.
      BibTeX arXiv
      • @article{Bralios2022nov,
      • author = {Bralios, Dimitrios and Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and Le Roux, Jonathan},
      • title = {Latent Iterative Refinement for Modular Source Separation},
      • journal = {arXiv},
      • year = 2022,
      • month = nov,
      • url = {https://arxiv.org/abs/2211.11917}
      • }
    See All Publications for Jonathan
  • Other Publications

    •  Masahiro Nakano, Jonathan Le Roux, Hirokazu Kameoka, Tomohiro Nakamura, Nobutaka Ono and Shigeki Sagayama, "Bayesian Nonparametric Spectrogram Modeling Based on Infinite Factorial Infinite Hidden Markov Model", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), October 2011.
      BibTeX
      • @Inproceedings{Nakano2011WASPAA10,
      • author = {Nakano, Masahiro and Le Roux, Jonathan and Kameoka, Hirokazu and Nakamura, Tomohiro and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Bayesian Nonparametric Spectrogram Modeling Based on Infinite Factorial Infinite Hidden Markov Model},
      • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
      • year = 2011,
      • month = oct
      • }
    •  Masahiro Nakano, Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono and Shigeki Sagayama, "Infinite-State Spectrum Model for Music Signal Analysis", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2011, pp. 1972-1975.
      BibTeX
      • @Inproceedings{Nakano2011ICASSP05,
      • author = {Nakano, Masahiro and Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Infinite-State Spectrum Model for Music Signal Analysis},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2011,
      • pages = {1972--1975},
      • month = may
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, Alain de Cheveigné and Shigeki Sagayama, "Computational Auditory Induction as a Missing-Data Model-Fitting Problem with Bregman Divergence", Speech Communication (Special issue on Perceptual and Statistical Audition), Vol. 53, No. 5, pp. 658-676, May-June 2011.
      BibTeX
      • @Article{LeRoux2011Specom05,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and de Cheveigne, Alain and Sagayama, Shigeki},
      • title = {Computational Auditory Induction as a Missing-Data Model-Fitting Problem with Bregman Divergence},
      • journal = {Speech Communication (Special issue on Perceptual and Statistical Audition)},
      • year = 2011,
      • volume = 53,
      • number = 5,
      • pages = {658--676},
      • month = {May-June}
      • }
    •  Hirokazu Kameoka, Takuya Yoshioka, Mariko Hamamura, Jonathan Le Roux and Kunio Kashino, "Statistical Model of Speech Signals Based on Composite Autoregressive System with Application to Blind Source Separation", International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), September 2010, pp. 245-253.
      BibTeX
      • @Inproceedings{Kameoka2010LVA09,
      • author = {Kameoka, Hirokazu and Yoshioka, Takuya and Hamamura, Mariko and Le Roux, Jonathan and Kashino, Kunio},
      • title = {Statistical Model of Speech Signals Based on Composite Autoregressive System with Application to Blind Source Separation},
      • booktitle = {International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA)},
      • year = 2010,
      • pages = {245--253},
      • month = sep
      • }
    •  Hirokazu Kameoka, Jonathan Le Roux and Yasunori Ohishi, "A Statistical Model of Speech F0 Contours", ISCA Tutorial and Research Workshop on Statistical And Perceptual Audition (SAPA), September 2010, pp. 43-48.
      BibTeX
      • @Inproceedings{Kameoka2010SAPA09,
      • author = {Kameoka, Hirokazu and Le Roux, Jonathan and Ohishi, Yasunori},
      • title = {A Statistical Model of Speech F0 Contours},
      • booktitle = {ISCA Tutorial and Research Workshop on Statistical And Perceptual Audition (SAPA)},
      • year = 2010,
      • pages = {43--48},
      • month = sep
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono and Shigeki Sagayama, "Fast Signal Reconstruction from Magnitude STFT Spectrogram Based on Spectrogram Consistency", International Conference on Digital Audio Effects (DAFx), September 2010, pp. 397-403.
      BibTeX
      • @Inproceedings{LeRoux2010DAFx09,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Fast Signal Reconstruction from Magnitude STFT Spectrogram Based on Spectrogram Consistency},
      • booktitle = {International Conference on Digital Audio Effects (DAFx)},
      • year = 2010,
      • pages = {397--403},
      • month = sep
      • }
    •  Jonathan Le Roux, Emmanuel Vincent, Yuu Mizuno, Hirokazu Kameoka, Nobutaka Ono and Shigeki Sagayama, "Consistent Wiener Filtering: Generalized Time-Frequency Masking Respecting Spectrogram Consistency", International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), September 2010, pp. 89-96.
      BibTeX
      • @Inproceedings{LeRoux2010LVA09,
      • author = {Le Roux, Jonathan and Vincent, Emmanuel and Mizuno, Yuu and Kameoka, Hirokazu and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Consistent Wiener Filtering: Generalized Time-Frequency Masking Respecting Spectrogram Consistency},
      • booktitle = {International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA)},
      • year = 2010,
      • pages = {89--96},
      • month = sep
      • }
    •  Masahiro Nakano, Jonathan Le Roux, Hirokazu Kameoka, Yu Kitano, Nobutaka Ono and Shigeki Sagayama, "Nonnegative Matrix Factorization with Markov-chained Bases for Modeling Time-varying patterns in Music Spectrograms", International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), September 2010, pp. 149-156.
      BibTeX
      • @Inproceedings{Nakano2010LVA09,
      • author = {Nakano, Masahiro and Le Roux, Jonathan and Kameoka, Hirokazu and Kitano, Yu and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Nonnegative Matrix Factorization with Markov-chained Bases for Modeling Time-varying patterns in Music Spectrograms},
      • booktitle = {International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA)},
      • year = 2010,
      • pages = {149--156},
      • month = sep
      • }
    •  Masahiro Nakano, Hirokazu Kameoka, Jonathan Le Roux, Yu Kitano, Nobutaka Ono and Shigeki Sagayama, "Convergence-Guaranteed Multiplicative Algorithms for Non-Negative Matrix Factorization with Beta-Divergence", IEEE International Workshop on Machine Learning for Signal Processing (MLSP), August 2010.
      BibTeX
      • @Inproceedings{Nakano2010MLSP08,
      • author = {Nakano, Masahiro and Kameoka, Hirokazu and Le Roux, Jonathan and Kitano, Yu and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Convergence-Guaranteed Multiplicative Algorithms for Non-Negative Matrix Factorization with Beta-Divergence},
      • booktitle = {IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
      • year = 2010,
      • month = aug
      • }
    •  Eric Carlen, Maria C. Carvalho, Jonathan Le Roux, Michael Loss and Cédric Villani, "Entropy and Chaos in the Kac Model", Kinetic and Related Models, Vol. 3, No. 1, pp. 85-122, March 2010.
      BibTeX
      • @Article{Carlen2010KRM03,
      • author = {Carlen, Eric and Carvalho, Maria C. and Le Roux, Jonathan and Loss, Michael and Villani, Cedric},
      • title = {Entropy and Chaos in the Kac Model},
      • journal = {Kinetic and Related Models},
      • year = 2010,
      • volume = 3,
      • number = 1,
      • pages = {85--122},
      • month = mar
      • }
    •  Nobutaka Ono, Kenichi Miyamoto, Hirokazu Kameoka, Jonathan Le Roux, Yuuki Uchiyama, Emiru Tsunoo, Takuya Nishimoto and Shigeki Sagayama, "Harmonic and Percussive Sound Separation and Its Application to MIR-Related Tasks" in Advances in Music Information Retrieval, Ras, Z. W. and Wieczorkowska, A., Eds., vol. 274 of Studies in Computational Intelligence, pp. 213-236, Springer, 2010.
      BibTeX
      • @Incollection{Ono2010Springer,
      • author = {Ono, Nobutaka and Miyamoto, Kenichi and Kameoka, Hirokazu and Le Roux, Jonathan and Uchiyama, Yuuki and Tsunoo, Emiru and Nishimoto, Takuya and Sagayama, Shigeki},
      • title = {Harmonic and Percussive Sound Separation and Its Application to MIR-Related Tasks},
      • booktitle = {Advances in Music Information Retrieval},
      • year = 2010,
      • editor = {Ras, Z. W. and Wieczorkowska, A.},
      • volume = 274,
      • series = {Studies in Computational Intelligence},
      • pages = {213--236},
      • publisher = {Springer}
      • }
    •  Jonathan Le Roux, "Exploiting Regularities in Natural Acoustical Scenes for Monaural Audio Signal Estimation, Decomposition, Restoration and Modification", March 2009, The University of Tokyo & Université Paris VI--Pierre et Marie Curie.
      BibTeX
      • @Phdthesis{LeRoux2009PhD03,
      • author = {Le Roux, Jonathan},
      • title = {Exploiting Regularities in Natural Acoustical Scenes for Monaural Audio Signal Estimation, Decomposition, Restoration and Modification},
      • school = {The University of Tokyo & Universite Paris VI--Pierre et Marie Curie},
      • year = 2009,
      • month = mar
      • }
    •  Jonathan Le Roux, Alain de Cheveigné and Lucas C. Parra, "Adaptive Template Matching with Shift-Invariant Semi-NMF", Advances in Neural Information Processing Systems (Proc. NIPS), Koller, D. and Bengio, Y. and Shuurmans, D. and Bottou, L., Eds., 2009.
      BibTeX
      • @Inproceedings{LeRoux2008NIPS12,
      • author = {Le Roux, Jonathan and de Cheveigne, Alain and Parra, Lucas C.},
      • title = {Adaptive Template Matching with Shift-Invariant Semi-NMF},
      • booktitle = {Advances in Neural Information Processing Systems (Proc. NIPS)},
      • year = 2009,
      • editor = {Koller, D. and Bengio, Y. and Shuurmans, D. and Bottou, L.},
      • address = {Cambridge, MA},
      • publisher = {The MIT Press}
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, Alain de Cheveigné and Shigeki Sagayama, "Computational Auditory Induction by Missing-Data Non-Negative Matrix Factorization", ISCA Workshop on Statistical and Perceptual Audition (SAPA), September 2008, pp. 1-6.
      BibTeX
      • @Inproceedings{LeRoux2008SAPA09a,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and de Cheveigne, Alain and Sagayama, Shigeki},
      • title = {Computational Auditory Induction by Missing-Data Non-Negative Matrix Factorization},
      • booktitle = {ISCA Workshop on Statistical and Perceptual Audition (SAPA)},
      • year = 2008,
      • pages = {1--6},
      • month = sep
      • }
    •  Jonathan Le Roux, Nobutaka Ono and Shigeki Sagayama, "Explicit Consistency Constraints for STFT Spectrograms and Their Application to Phase Reconstruction", ISCA Workshop on Statistical and Perceptual Audition (SAPA), September 2008, pp. 23-28.
      BibTeX
      • @Inproceedings{LeRoux2008SAPA09b,
      • author = {Le Roux, Jonathan and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Explicit Consistency Constraints for STFT Spectrograms and Their Application to Phase Reconstruction},
      • booktitle = {ISCA Workshop on Statistical and Perceptual Audition (SAPA)},
      • year = 2008,
      • pages = {23--28},
      • month = sep
      • }
    •  Nobutaka Ono, Ken-Ichi Miyamoto, Jonathan Le Roux, Hirokazu Kameoka and Shigeki Sagayama, "Separation of a Monaural Audio Signal into Harmonic/Percussive Components by Complementary Diffusion on Spectrogram", European Signal Processing Conference (EUSIPCO), August 2008.
      BibTeX
      • @Inproceedings{Ono2008EUSIPCO08,
      • author = {Ono, Nobutaka and Miyamoto, Ken-Ichi and Le Roux, Jonathan and Kameoka, Hirokazu and Sagayama, Shigeki},
      • title = {Separation of a Monaural Audio Signal into Harmonic/Percussive Components by Complementary Diffusion on Spectrogram},
      • booktitle = {European Signal Processing Conference (EUSIPCO)},
      • year = 2008,
      • month = aug
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, Shigeki Sagayama and Alain de Cheveigné, "Modulation Analysis of Speech Through Orthogonal FIR Filterbank Optimization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2008, pp. 4189-4192.
      BibTeX
      • @Inproceedings{LeRoux2008ICASSP04,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and Sagayama, Shigeki and de Cheveigne, Alain},
      • title = {Modulation Analysis of Speech Through Orthogonal FIR Filterbank Optimization},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2008,
      • pages = {4189--4192},
      • month = apr
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono and Shigeki Sagayama, "On the Interpretation of I-Divergence-Based Distribution-Fitting as a Maximum-Likelihood Estimation Problem," Tech. Rep. METR 2008-11, The University of Tokyo, March 2008.
      BibTeX
      • @Techreport{LeRoux2008TechRep03,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {On the Interpretation of I-Divergence-Based Distribution-Fitting as a Maximum-Likelihood Estimation Problem},
      • institution = {The University of Tokyo},
      • year = 2008,
      • number = {METR 2008-11},
      • month = mar
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, Alain de Cheveigné and Shigeki Sagayama, "Single Channel Speech and Background Segregation through Harmonic-Temporal Clustering", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), October 2007, pp. 279-282.
      BibTeX
      • @Inproceedings{LeRoux2007WASPAA10,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and de Cheveigne, Alain and Sagayama, Shigeki},
      • title = {Single Channel Speech and Background Segregation through Harmonic-Temporal Clustering},
      • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
      • year = 2007,
      • pages = {279--282},
      • month = oct
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, Alain de Cheveigné and Shigeki Sagayama, "Single and Multiple F0 Contour Estimation Through Parametric Spectrogram Modeling of Speech in Noisy Environments", IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 4, pp. 1135-1145, May 2007.
      BibTeX
      • @Article{LeRoux2007IEEETASLP05,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and de Cheveigne, Alain and Sagayama, Shigeki},
      • title = {Single and Multiple F0 Contour Estimation Through Parametric Spectrogram Modeling of Speech in Noisy Environments},
      • journal = {IEEE Transactions on Audio, Speech and Language Processing},
      • year = 2007,
      • volume = 15,
      • number = 4,
      • pages = {1135--1145},
      • month = may
      • }
    •  Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, Alain de Cheveigné and Shigeki Sagayama, "Harmonic-Temporal Clustering of Speech for Single and Multiple F0 Contour Estimation in Noisy Environments", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2007, vol. 4, pp. 1053-1056.
      BibTeX
      • @Inproceedings{LeRoux2007ICASSP04,
      • author = {Le Roux, Jonathan and Kameoka, Hirokazu and Ono, Nobutaka and de Cheveigne, Alain and Sagayama, Shigeki},
      • title = {Harmonic-Temporal Clustering of Speech for Single and Multiple F0 Contour Estimation in Noisy Environments},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2007,
      • volume = 4,
      • pages = {1053--1056},
      • month = apr
      • }
    •  Alain de Cheveigné, Jonathan Le Roux and Jonathan Z. Simon, "MEG Signal Denoising based on Time-Shift PCA", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2007, vol. 1, pp. 317-320.
      BibTeX
      • @Inproceedings{deCheveigne2007ICASSP04,
      • author = {de Cheveigne, Alain and Le Roux, Jonathan and Simon, Jonathan Z.},
      • title = {MEG Signal Denoising based on Time-Shift PCA},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2007,
      • volume = 1,
      • pages = {317--320},
      • month = apr
      • }
    •  Erik McDermott, Timothy J. Hazen, Jonathan Le Roux, Atsushi Nakamura and Shigeru Katagiri, "Discriminative Training for Large Vocabulary Speech Recognition Using Minimum Classification Error", IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 1, pp. 203-223, January 2007.
      BibTeX
      • @Article{McDermott2007IEEETASLP03,
      • author = {McDermott, Erik and Hazen, Timothy J. and Le Roux, Jonathan and Nakamura, Atsushi and Katagiri, Shigeru},
      • title = {Discriminative Training for Large Vocabulary Speech Recognition Using Minimum Classification Error},
      • journal = {IEEE Transactions on Audio, Speech and Language Processing},
      • year = 2007,
      • volume = 15,
      • number = 1,
      • pages = {203--223},
      • month = jan
      • }
    •  Hirokazu Kameoka, Jonathan Le Roux, Nobutaka Ono and Shigeki Sagayama, "Speech Analyzer Using a Joint Estimation Model of Spectral Envelope and Fine Structure", ISCA International Conference on Spoken Language Processing (ICSLP/Interspeech), September 2006, pp. 2502-2505.
      BibTeX
      • @Inproceedings{Kameoka2006Interspeech09,
      • author = {Kameoka, Hirokazu and Le Roux, Jonathan and Ono, Nobutaka and Sagayama, Shigeki},
      • title = {Speech Analyzer Using a Joint Estimation Model of Spectral Envelope and Fine Structure},
      • booktitle = {ISCA International Conference on Spoken Language Processing (ICSLP/Interspeech)},
      • year = 2006,
      • pages = {2502--2505},
      • month = sep
      • }
    •  Jonathan Le Roux and Erik McDermott, "Optimization Methods for Discriminative Training", ISCA European Conference on Speech Communication and Technology (Eurospeech/Interspeech), September 2005, pp. 3341-3344.
      BibTeX
      • @Inproceedings{LeRoux2005Eurospeech09,
      • author = {Le Roux, Jonathan and McDermott, Erik},
      • title = {Optimization Methods for Discriminative Training},
      • booktitle = {ISCA European Conference on Speech Communication and Technology (Eurospeech/Interspeech)},
      • year = 2005,
      • pages = {3341--3344},
      • month = sep
      • }
  • Software Downloads

  • Videos

  • MERL Issued Patents

    • Title: "Scene-Aware Video Encoder System and Method"
      Inventors: Cherian, Anoop; Hori, Chiori; Le Roux, Jonathan; Marks, Tim; Sullivan, Alan
      Patent No.: 11,582,485
      Issue Date: Feb 14, 2023
    • Title: "Manufacturing Automation using Acoustic Separation Neural Network"
      Inventors: Wichern, Gordon P; Le Roux, Jonathan; Pishdadian, Fatemeh
      Patent No.: 11,579,598
      Issue Date: Feb 14, 2023
    • Title: "An Artificial Intelligence System for Capturing Context by Dilated Self-Attention"
      Inventors: Moritz, Niko; Hori, Takaaki; Le Roux, Jonathan
      Patent No.: 11,557,283
      Issue Date: Jan 17, 2023
    • Title: "System and Method for Hierarchical Audio Source Separation"
      Inventors: Wichern, Gordon P; Le Roux, Jonathan; Manilow, Ethan
      Patent No.: 11,475,908
      Issue Date: Oct 18, 2022
    • Title: "System and Method for Detecting Adversarial Attacks"
      Inventors: Le Roux, Jonathan; Jayashankar, Tejas; Moulin, Pierre
      Patent No.: 11,462,211
      Issue Date: Oct 4, 2022
    • Title: "Low-latency Captioning System"
      Inventors: Hori, Chiori; Hori, Takaaki; Cherian, Anoop; Marks, Tim; Le Roux, Jonathan
      Patent No.: 11,445,267
      Issue Date: Sep 13, 2022
    • Title: "System and Method for Streaming end-to-end Speech Recognition with Asynchronous Decoders"
      Inventors: Moritz, Niko; Hori, Takaaki; Le Roux, Jonathan
      Patent No.: 11,373,639
      Issue Date: Jun 28, 2022
    • Title: "Scene-Aware Video Dialog"
      Inventors: Geng, Shijie; Gao, Peng; Cherian, Anoop; Hori, Chiori; Le Roux, Jonathan
      Patent No.: 11,210,523
      Issue Date: Dec 28, 2021
    • Title: "System and Method for End-to-End Speech Recognition with Triggered Attention"
      Inventors: Moritz, Niko; Hori, Takaaki; Le Roux, Jonathan
      Patent No.: 11,100,920
      Issue Date: Aug 24, 2021
    • Title: "Method and System for Multi-Label Classification"
      Inventors: Hori, Takaaki; Hori, Chiori; Watanabe, Shinji; Hershey, John R.; Harsham, Bret A.; Le Roux, Jonathan
      Patent No.: 11,086,918
      Issue Date: Aug 10, 2021
    • Title: "Methods and Systems for Recognizing Simultaneous Speech by Multiple Speakers"
      Inventors: Le Roux, Jonathan; Hori, Takaaki; Settle, Shane; Seki, Hiroshi; Watanabe, Shinji; Hershey, John R.
      Patent No.: 10,811,000
      Issue Date: Oct 20, 2020
    • Title: "Methods and Systems for Enhancing Audio Signals Corrupted by Noise"
      Inventors: Le Roux, Jonathan; Watanabe, Shinji; Hershey, John R.; Wichern, Gordon P
      Patent No.: 10,726,856
      Issue Date: Jul 28, 2020
    • Title: "Method and Apparatus for Multi-Lingual End-to-End Speech Recognition"
      Inventors: Watanabe, Shinji; Hori, Takaaki; Seki, Hiroshi; Le Roux, Jonathan; Hershey, John R.
      Patent No.: 10,593,321
      Issue Date: Mar 17, 2020
    • Title: "Neural Networks for Transforming Signals"
      Inventors: Le Roux, Jonathan; Hershey, John R.; Weninger, Felix
      Patent No.: 10,592,800
      Issue Date: Mar 17, 2020
    • Title: "Methods and Systems for End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction"
      Inventors: Le Roux, Jonathan; Hershey, John R.; Wang, Zhongqiu; Wichern, Gordon P
      Patent No.: 10,529,349
      Issue Date: Jan 7, 2020
    • Title: "Method for Enhancing Audio Signal using Phase Information"
      Inventors: Erdogan, Hakan; Hershey, John R.; Watanabe, Shinji; Le Roux, Jonathan
      Patent No.: 9,881,631
      Issue Date: Jan 30, 2018
    • Title: "Method for Distinguishing Components of an Acoustic Signal"
      Inventors: Hershey, John R.; Le Roux, Jonathan; Watanabe, Shinji; Chen, Zhuo
      Patent No.: 9,685,155
      Issue Date: Jun 20, 2017
    • Title: "Source Signal Separation by Discriminatively-Trained Non-Negative Matrix Factorization"
      Inventors: Le Roux, Jonathan; Hershey, John R.; Weninger, Felix; Watanabe, Shinji
      Patent No.: 9,679,559
      Issue Date: Jun 13, 2017
    • Title: "Flat-Panel Acoustic Apparatus"
      Inventors: Le Roux, Jonathan; Hershey, John R.; Yerazunis, William S.; Boufounos, Petros T.; Daudet, Laurent
      Patent No.: 9,661,414
      Issue Date: May 23, 2017
    • Title: "Method for Processing Speech Signals Using an Ensemble of Speech Enhancement Procedures"
      Inventors: Le Roux, Jonathan; Watanabe, Shinji; Hershey, John R.
      Patent No.: 9,601,130
      Issue Date: Mar 21, 2017
    • Title: "Neural Networks for Transforming Signals"
      Inventors: Hershey, John R.; Le Roux, Jonathan; Weninger, Felix
      Patent No.: 9,582,753
      Issue Date: Feb 28, 2017
    • Title: "Method and System for Detecting Events in an Acoustic Signal Subject to Cyclo-Stationary Noise"
      Inventors: Hershey, John R.; Potluru, Vamsi K.; Le Roux, Jonathan
      Patent No.: 9,477,895
      Issue Date: Oct 25, 2016
    • Title: "Actions Prediction for Hypothetical Driving Conditions"
      Inventors: Harsham, Bret A.; Hershey, John R.; Le Roux, Jonathan; Nikovski, Daniel N.; Esenther, Alan W.
      Patent No.: 9,434,389
      Issue Date: Sep 6, 2016
    • Title: "Method for Distinguishing Components of an Acoustic Signal"
      Inventors: Hershey, John R.; Le Roux, Jonathan; Watanabe, Shinji; Chen, Zhuo
      Patent No.: 9,368,110
      Issue Date: Jun 14, 2016
    • Title: "Denoising Noisy Speech Signals using Probabilistic Model"
      Inventors: Le Roux, Jonathan; Hershey, John R.; Simsekli, Umut
      Patent No.: 9,324,338
      Issue Date: Apr 26, 2016
    • Title: "Method for Localizing Sources of Signals in Reverberant Environments Using Sparse Optimization"
      Inventors: Boufounos, Petros T.; Le Roux, Jonathan; Kang, Kang; Hershey, John R.
      Patent No.: 9,251,436
      Issue Date: Feb 2, 2016
    • Title: "Method and Apparatus for Processing Text with Variations in Vocabulary Usage"
      Inventors: Hershey, John R.; Le Roux, Jonathan; Heakulani, Creighton K.
      Patent No.: 9,251,250
      Issue Date: Feb 2, 2016
    • Title: "Method and System for Dynamically Adapting user Interfaces in Vehicle Navigation Systems to Minimize Interaction Complexity"
      Inventors: Nikovski, Daniel N.; Hershey, John R.; Harsham, Bret A.; Le Roux, Jonathan
      Patent No.: 9,170,119
      Issue Date: Oct 27, 2015
    • Title: "Method of Text Classification Using Discriminative Topic Transformation"
      Inventors: Hershey, John R.; Le Roux, Jonathan
      Patent No.: 9,069,798
      Issue Date: Jun 30, 2015
    • Title: "Indirect Model-Based Speech Enhancement"
      Inventors: Hershey, John R.; Le Roux, Jonathan
      Patent No.: 8,880,393
      Issue Date: Nov 4, 2014
    See All Patents for MERL