Acoustic Scene Analysis

2019-04-07, Sunday

Today, a new module to estimate and analysis of the fundamental frequency (F0) of speech signals has been added. Two different estimators are supported with a various set of adjustable parameters. Additionally, a gender detector is implemented, and intonation analysis is available. All the estimation parameters can be manually configured using GUI widgets. After the estimation process, a set of statistical properties of F0 can be used to generate feature space for voice analysis.

faaw f0 analysis

2019-02-12, Tuesday

Annotation tool and calculator with several acoustic-related functions were added to FAAW. The notes are assigned to file which name is highlighted in the list if any annotations were made. The data exchange between a displayed representation, calculator and annotation tool is also possible. The annotations are stored in the currently analysed repository.

faaw annotation
faaw calc

2019-01-18, Friday

Rewriting many parts of the code has been done. A few caching mechanisms improved the speed of calculations and responsiveness of the application. The usability of diagrams analysis has been significantly improved. Also, several new representations were introduced, and a new peaks detection algorithm with the enhanced statistical module was added.

2018-10-07, Sunday

faaw icv

A new module has been implemented and added to FAAW.

The purpose of a new tool is to determine how attributes of selected representation vary between classes. Such functionality can be used to select attributes with small variability inside a selected class and with high variability between different classes.

2018-09-21, Friday

The challenge results are just published. Our system has been ranked at 39th position with accuracy equal to 65.8 % (64.3 - 67.4). The paper entitled "Audio Feature Space Analysis for Acoustic Scene Classification"  has been accepted and the results will be presented at the poster session of the DCASE workshop held in Woking, Surrey, UK.

2018-08-16, Thursday

ASA browser has been redesigned and rewritten. The new version called FAAW is still under development using Python/C++ languages.

Current features:

  • Highly configurable parametrisation stage. The acoustic features are computed in the C++ module, and at the moment, it supports 580 representations.
  • Convenient interface with mouse-free navigation.
  • The parameters of feature space are configurable in YAMLs files.
  • Editable text notes per audio file.
  • Easy access to audio files for inspection and annotation.
  • Various graphical representations of audio features.
faaw main window

2018-08-01, Wednesday

The results for Task 1A (classification of data from the same device as the available training data) of DCASE competition have been sent. The designed system uses traditional ML approach using carefully crafted audio feature space contained 223 attributes. Also, we have submitted a paper to the DCASE workshop.

2018-07-20, Friday

For this year DCASE Challenge, we have designed and implemented an auxiliary tool (ASA browser) to generate and analyse a feature space. The primary long-term goal is to support a semi-automatic process of finding associations between attributes and support the process of creating hierarchical features. The tool is in the early stage of development and is not available for download yet. At the current stage, the browser is capable of generating numerical values for the dataset and displaying several acoustical representations grouped by classes and locations.

The following screenshots show example representations for few audio files of the development dataset released for DCASE 2018 competition.

asa browser (1)
asa browser (2)
asa browser (3)
asa browser (4)
asa browser (5)
asa browser (6)