Speech & Audio

Audio source separation, recognition, and understanding.

Our current research focuses on application of machine learning to estimation and inference problems in speech and audio processing. Topics include end-to-end speech recognition and enhancement, acoustic modeling and analysis, statistical dialog systems, as well as natural language understanding and adaptive multimodal interfaces.

  • Researchers

  • 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.
    •  

    See All Awards for Speech & Audio
  • News & Events

    •  NEWS   Anoop Cherian gave an invited talk at the Multi-modal Video Analysis Workshop, ECCV 2020
      Date: August 23, 2020
      Where: European Conference on Computer Vision (ECCV), online, 2020
      MERL Contact: Anoop Cherian
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
      Brief
      • MERL Principal Research Scientist Anoop Cherian gave an invited talk titled "Sound2Sight: Audio-Conditioned Visual Imagination" at the Multi-modal Video Analysis workshop held in conjunction with the European Conference on Computer Vision (ECCV), 2020. The talk was based on a recent ECCV paper that describes a new multimodal reasoning task called Sound2Sight and a generative adversarial machine learning algorithm for producing plausible video sequences conditioned on sound and visual context.
    •  
    •  NEWS   MERL's Scene-Aware Interaction Technology Featured in Mitsubishi Electric Corporation Press Release
      Date: July 22, 2020
      Where: Tokyo, Japan
      MERL Contacts: Siheng Chen; Anoop Cherian; Bret Harsham; Chiori Hori; Takaaki Hori; Jonathan Le Roux; Tim Marks; Alan Sullivan; Anthony Vetro
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Speech & Audio
      Brief
      • Mitsubishi Electric Corporation announced that the company has developed what it believes to be the world’s first technology capable of highly natural and intuitive interaction with humans based on a scene-aware capability to translate multimodal sensing information into natural language.

        The novel technology, Scene-Aware Interaction, incorporates Mitsubishi Electric’s proprietary Maisart® compact AI technology to analyze multimodal sensing information for highly natural and intuitive interaction with humans through context-dependent generation of natural language. The technology recognizes contextual objects and events based on multimodal sensing information, such as images and video captured with cameras, audio information recorded with microphones, and localization information measured with LiDAR.

        Scene-Aware Interaction for car navigation, one target application, will provide drivers with intuitive route guidance. The technology is also expected to have applicability to human-machine interfaces for in-vehicle infotainment, interaction with service robots in building and factory automation systems, systems that monitor the health and well-being of people, surveillance systems that interpret complex scenes for humans and encourage social distancing, support for touchless operation of equipment in public areas, and much more. The technology is based on recent research by MERL's Speech & Audio and Computer Vision groups.


        Demonstration Video:



        Link:

        Mitsubishi Electric Corporation Press Release
    •  

    See All News & Events for Speech & Audio
  • Research Highlights

  • Internships

    • SA1471: End-to-end speech and audio processing for new and challenging environments

      MERL is looking for interns to work on fundamental research in the area of end-to-end speech and audio processing for new and challenging environments using advanced machine learning techniques. The intern will collaborate with MERL researchers to derive and implement new models and learning methods, conduct experiments, and prepare results for high impact publication. The ideal candidates would be senior Ph.D. students with experience in one or more of automatic speech recognition, speech enhancement, sound event detection, and natural language processing, including good theoretical and practical knowledge of relevant machine learning algorithms with related programming skills. The duration of the internship is expected to be 3-6 months. Positions are available immediately and throughout 2021.

    • SA1473: Multi-modal scene understanding

      We are looking for a graduate student interested in helping advance the field of multi-modal scene understanding, with a focus on detailed captioning of a scene using natural language. The intern will collaborate with MERL researchers to derive and implement new models and optimization methods, conduct experiments, and prepare results for publication. The ideal candidate would be a senior Ph.D. student with experience in deep learning for audio-visual, signal and natural language processing. The expected duration of the internship is 3-6 months, and start date is flexible.

    • SA1469: Audio source separation and sound event detection

      We are seeking multiple graduate students interested in helping advance the fields of source separation, speech enhancement, and sound event detection/localization in challenging multi-source and far-field scenarios. The intern will collaborate with MERL researchers to derive and implement new models and optimization methods, conduct experiments, and prepare results for publication. The ideal candidate would be a senior Ph.D. student with experience in audio signal processing, microphone array processing, probabilistic modeling, and deep learning techniques requiring minimal supervision (e.g., unsupervised, weakly-supervised, self-supervised, or few shot learning). The expected duration of the internship is 3-6 months and start date is flexible.


    See All Internships for Speech & Audio
  • Recent Publications

    •  Hori, T., Moritz, N., Hori, C., Le Roux, J., "Transformer-based Long-context End-to-end Speech Recognition", Annual Conference of the International Speech Communication Association (Interspeech), October 2020.
      BibTeX TR2020-139 PDF
      • @inproceedings{Hori2020oct,
      • author = {Hori, Takaaki and Moritz, Niko and Hori, Chiori and Le Roux, Jonathan},
      • title = {Transformer-based Long-context End-to-end Speech Recognition},
      • booktitle = {Annual Conference of the International Speech Communication Association (Interspeech)},
      • year = 2020,
      • month = oct,
      • url = {https://www.merl.com/publications/TR2020-139}
      • }
    •  Jayashankar, T., Le Roux, J., Moulin, P., "Detecting Audio Attacks on ASR Systems with Dropout Uncertainty", Annual Conference of the International Speech Communication Association (Interspeech), October 2020.
      BibTeX TR2020-137 PDF
      • @inproceedings{Jayashankar2020oct,
      • author = {Jayashankar, Tejas and Le Roux, Jonathan and Moulin, Pierre},
      • title = {Detecting Audio Attacks on ASR Systems with Dropout Uncertainty},
      • booktitle = {Annual Conference of the International Speech Communication Association (Interspeech)},
      • year = 2020,
      • month = oct,
      • url = {https://www.merl.com/publications/TR2020-137}
      • }
    •  Moritz, N., Wichern, G., Hori, T., Le Roux, J., "All-in-One Transformer: Unifying Speech Recognition, Audio Tagging, and Event Detection", Annual Conference of the International Speech Communication Association (Interspeech), October 2020.
      BibTeX TR2020-138 PDF
      • @inproceedings{Moritz2020oct,
      • author = {Moritz, Niko and Wichern, Gordon and Hori, Takaaki and Le Roux, Jonathan},
      • title = {All-in-One Transformer: Unifying Speech Recognition, Audio Tagging, and Event Detection},
      • booktitle = {Annual Conference of the International Speech Communication Association (Interspeech)},
      • year = 2020,
      • month = oct,
      • url = {https://www.merl.com/publications/TR2020-138}
      • }
    •  Manilow, E., Wichern, G., Le Roux, J., "Hierarchical Musical Instrument Separation", International Society for Music Information Retrieval (ISMIR) Conference, October 2020.
      BibTeX TR2020-136 PDF
      • @inproceedings{Manilow2020oct,
      • author = {Manilow, Ethan and Wichern, Gordon and Le Roux, Jonathan},
      • title = {Hierarchical Musical Instrument Separation},
      • booktitle = {International Society for Music Information Retrieval (ISMIR) Conference},
      • year = 2020,
      • month = oct,
      • url = {https://www.merl.com/publications/TR2020-136}
      • }
    •  Seetharaman, P., Wichern, G., Pardo, B., Le Roux, J., "Autoclip: Adaptive Gradient Clipping For Source Separation Networks", IEEE International Workshop on Machine Learning for Signal Processing (MLSP), September 2020.
      BibTeX TR2020-132 PDF
      • @inproceedings{Seetharaman2020sep,
      • author = {Seetharaman, Prem and Wichern, Gordon and Pardo, Bryan and Le Roux, Jonathan},
      • title = {Autoclip: Adaptive Gradient Clipping For Source Separation Networks},
      • booktitle = {IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
      • year = 2020,
      • month = sep,
      • url = {https://www.merl.com/publications/TR2020-132}
      • }
    •  Pishdadian, F., Wichern, G., Le Roux, J., "Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision", IEEE/ACM Transactions on Audio, Speech, and Language Processing, September 2020.
      BibTeX TR2020-126 PDF
      • @article{Pishdadian2020sep,
      • author = {Pishdadian, Fatemeh and Wichern, Gordon and Le Roux, Jonathan},
      • title = {Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision},
      • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
      • year = 2020,
      • month = sep,
      • url = {https://www.merl.com/publications/TR2020-126}
      • }
    •  Seetharaman, P., Wichern, G., Le Roux, J., Pardo, B., "Bootstrapping Unsupervised Deep Music Separation from Primitive Auditory Grouping Principles", ICML 2020 Workshop on Self-supervision in Audio and Speech, July 2020.
      BibTeX TR2020-111 PDF
      • @inproceedings{Seetharaman2020jul,
      • author = {Seetharaman, Prem and Wichern, Gordon and Le Roux, Jonathan and Pardo, Bryan},
      • title = {Bootstrapping Unsupervised Deep Music Separation from Primitive Auditory Grouping Principles},
      • booktitle = {ICML 2020 Workshop on Self-supervision in Audio and Speech},
      • year = 2020,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2020-111}
      • }
    •  Chang, X., Zhang, W., Qian, Y., Le Roux, J., Watanabe, S., "End-To-End Multi-Speaker Speech Recognition with Transformer", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9054029, April 2020, pp. 6134-6138.
      BibTeX TR2020-043 PDF Video
      • @inproceedings{Chang2020apr,
      • author = {Chang, Xuankai and Zhang, Wangyou and Qian, Yanmin and Le Roux, Jonathan and Watanabe, Shinji},
      • title = {End-To-End Multi-Speaker Speech Recognition with Transformer},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2020,
      • pages = {6134--6138},
      • month = apr,
      • publisher = {IEEE},
      • doi = {10.1109/ICASSP40776.2020.9054029},
      • issn = {2379-190X},
      • isbn = {978-1-5090-6631-5},
      • url = {https://www.merl.com/publications/TR2020-043}
      • }
    See All Publications for Speech & Audio
  • Videos

  • Software Downloads