Justin Salamon
  • Home
  • News
  • Research
  • Publications
  • Code/Data
  • Melody Extraction
  • PhD Thesis
  • Contact
    • Music
    • Music Technology

Per-Channel Energy Normalization: Why and how

29/10/2018

0 Comments

 
In the context of automatic speech recognition and acoustic event detection, an adaptive procedure named per-channel energy normalization (PCEN) has recently shown to outperform the pointwise logarithm of mel-frequency spectrogram (logmelspec) as an acoustic frontend. This article investigates the adequacy of PCEN for spectrogram-based pattern recognition in far-field noisy recordings, both from theoretical and practical standpoints. First, we apply PCEN on various datasets of natural acoustic environments and find empirically that it Gaussianizes distributions of magnitudes while decorrelating frequency bands. Secondly, we describe the asymptotic regimes of each component in PCEN: temporal integration, gain control, and dynamic range compression. Thirdly, we give practical advice for adapting PCEN parameters to the temporal properties of the noise to be mitigated, the signal to be enhanced, and the choice of time-frequency representation. As it converts a large class of real-world soundscapes into additive white Gaussian noise (AWGN), PCEN is a computationally efficient frontend for robust detection and classification of acoustic events in heterogeneous environments.

Read the full paper here:

Per-Channel Energy Normalization: Why and how
V. Lostanlen, J. Salamon, M. Cartwright, B. McFee, A. Farnsworth, S. Kelling, and J. P. Bello.
IEEE Signal Processing Letters, 26(1): 39–43, Jan. 2019.
​[IEEE][PDF][BibTeX][Copyright]

Here's a plot from our paper comparing the application of log vs PCEN on a mel-spectrogram computed from an audio recording captured by a remote acoustic sensor for avian flight call detection (as part of our BirdVox project). In the top plot (log) we clearly see energy from undesired noise sources such as insects and a car, whereas in the bottom plot (PCEN) we see these confounding factors have been attenuated, while the flight calls we wish to detect (which appear as very short chirps) are kept.
Picture
Fig. 1. A soundscape comprising bird calls, insect stridulations, and a passing vehicle. The logarithmic transformation of the mel-frequency spectrogram (a) maps all magnitudes to a decibel-like scale, whereas per-channel energy normalization (b) enhances transient events (bird calls) while discarding stationary noise (insects) as well as slow changes in loudness (vehicle). Data provided by BirdVox. Mel-frequency spectrogram and PCEN computed with default librosa 0.6.1 parameters and T = 60 ms (see Section IV).
0 Comments

Robust Sound Event Detection in Acoustic Sensor Networks

18/10/2018

0 Comments

 
On Thursday October 18th I'll be giving a talk at the Speech and Audio in the Northeast (SANE) 2018 workshop hosted by Google Boston, covering some of our most recent work on sound recognition with acoustic sensor networks as part of the SONYC and BirdVox projects. Hope you can join us!

Abstract:
The combination of remote acoustic sensors with automatic sound recognition represents a powerful emerging technology for studying both natural and urban environments. At NYU we've been working on two projects whose aim is to develop and leverage this technology:  the Sounds of New York City (SONYC) project is using acoustic sensors to understand noise patterns across NYC to improve noise mitigation efforts, and the BirdVox project is using them for the purpose of tracking bird migration patterns in collaboration with the Cornell Lab of Ornithology. Acoustic sensors present both unique opportunities and unique challenges when it comes to developing machine listening algorithms for automatic sound event detection: they facilitate the collection of large quantities of audio data, but the data is unlabeled, constraining our ability to leverage supervised machine learning algorithms. Training generalizable models becomes particularly challenging when training data come from a limited set of sensor locations (and times), and yet our models must generalize to unseen natural and urban environments with unknown and sometimes surprising confounding factors. In this talk I will present our work towards tackling these challenges along several different lines with neural network architectures, including novel pooling layers that allow us to better leverage weakly labeled training data, self-supervised audio embeddings that allow us to train high-accuracy models with a limited amount of labeled data, and context-adaptive networks that improve the robustness of our models to heterogenous acoustic environments.

​UPDATE: thanks everyone for attending the talk! Here are a video recording of the talk as well as the slides:
Robust Sound Event Detection in Acoustic Sensor Networks
Justin Salamon
Speech and Audio in the Northeast (SANE), Google, Cambridge, MA, Oct. 2018
[slides]
Picture
Picture
0 Comments

    NEWS

    Machine listening research, code, data & hacks!

    Archives

    March 2023
    April 2022
    November 2021
    October 2021
    June 2021
    January 2021
    October 2020
    June 2020
    May 2020
    April 2020
    January 2020
    November 2019
    October 2019
    June 2019
    May 2019
    March 2019
    February 2019
    January 2019
    November 2018
    October 2018
    August 2018
    July 2018
    May 2018
    April 2018
    February 2018
    October 2017
    August 2017
    July 2017
    June 2017
    April 2017
    March 2017
    January 2017
    December 2016
    November 2016
    October 2016
    August 2016
    June 2016
    May 2016
    April 2016
    February 2016
    January 2016
    November 2015
    October 2015
    July 2015
    June 2015
    April 2015
    February 2015
    November 2014
    October 2014
    September 2014
    June 2014
    April 2014
    March 2014
    February 2014
    December 2013
    September 2013
    July 2013
    May 2013
    February 2013
    January 2013
    December 2012
    November 2012
    October 2012
    August 2012
    July 2012
    June 2012

    Categories

    All
    ACM MM'13
    ACM MM'14
    Acoustic Ecology
    Acoustic Event Detection
    Acoustic Sensing
    AES
    Applied Acoustics
    Article
    Audio-annotator
    Audio To Midi
    Auditory Scene Analysis
    Avian
    Award
    Baseball
    Beer
    Best Oral Presentation
    Best Paper Award
    Best Student Paper Award
    BigApps
    Bioacoustics
    BirdVox
    Book
    Chapter
    CHI
    Citizen Science
    Classification
    Computer Vision
    Conference
    Connected Cities
    Convolutional Neural Networks
    Cornell Lab Of Ornithology
    Coursera
    Cover Detection
    CREPE
    Crowdcrafting
    Crowdsourcing
    CUSP
    CVPR
    Data Augmentation
    Data Science
    Dataset
    Data Structures
    Dcase
    Deep Learning
    Domain
    Education
    Entrepreneurship
    Environmental Sound
    Essentia
    Eusipco
    Eusipco2015
    Evaluation
    Few-shot Learning
    Flight Calls
    Girl Scouts
    Grant
    Hackathon
    Hackday
    Hackfest
    HCI
    Hildegard Von Bingen
    ICASSP
    ICASSP 2020
    IEEE Signal Processing Letters
    Ieee Spm
    Indian Classical Music
    Interface
    Interspeech
    Interview
    Ismir 2012
    Ismir2014
    Ismir2015
    Ismir2016
    Ismir2017
    Ismir2020
    ITP
    Jams
    Javascript
    JNMR
    Journal
    Machine Learning
    Machine Listening
    Map
    Media
    Melodia
    Melody Extraction
    Metric Learning
    Midi
    Migration Monitoring
    MIR
    Mir_eval
    MOOC
    MTG-QBH
    Music Informatics
    Music Information Retrieval
    Music Similarity
    National Science Foundation
    Neumerator
    New York Times
    Noise Pollution
    Notebook
    NPR
    NSF
    NYC
    NYU
    Open Source
    Pitch
    Pitch Contours
    Pitch Tracking
    Plos One
    Plug In
    Plug-in
    Presentation
    Press
    PRI
    Prosody
    Publication
    Python
    Query By Humming
    Query-by-humming
    Radio
    Representation Learning
    Research
    Robots
    Scaper
    Science And The City
    Science Friday
    Self-supervision
    Sensor Network
    Sensors
    Sight And Sound Workshop
    Smart Cities
    Software
    SONYC
    Sound Classification
    Sound Education
    Sound Event Detection
    Soundscape
    Sounds Of New York City
    Sound Workshop
    Speech
    STEM
    Synthesis
    Taste Of Science
    Taxonomy
    Technical Report
    Time Series
    Tonic ID
    Tony
    Tutorial
    Unsupervised Feature Learning
    Urban
    Urban Sound Analysis
    Urban Sound Tagging
    Vamp
    Version Identification
    Visualization
    Vocaloid
    Vocoder
    Warblers
    Wav To Midi
    Welcome
    Wired
    WNYC
    Women In Science
    Workshop
    World Domination
    Wsf14
    Youtube

    RSS Feed

Powered by Create your own unique website with customizable templates.
  • Home
  • News
  • Research
  • Publications
  • Code/Data
  • Melody Extraction
  • PhD Thesis
  • Contact
    • Music
    • Music Technology