Veronica Morfi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Veronica Morfi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Dan Stowell
Naturalis Biodiversity Center Leiden The Netherlands
8 shared publications Athanasios Mouchtaris
Computer Science Department, University of Crete, and Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH-ICS), Heraklion, Greece
2 shared publications- Gilles Degottex
IRCAM - CNRS-UMR9912-STMS, Analysis-Synthesis Team, 1, place Igor Stravinsky, 75004 Paris, France
2 shared publications - David F. Clayton
Clemson University 5 Department of Genetics and Biochemistry Clemson, SC 29634
1 shared publication Hanna Pamuła
Department of Mechanics and Vibroacoustics, AGH University of Science and Technology, Kraków, Poland
1 shared publication- Hervé Glotin
DYNI team, LIS laboratory (CMR 7020), Aix-Marseille and Toulon university, France
1 shared publication
Latest Publications
- Open Access
Bird song comparison using deep learning trained from avian perceptual judgments
Our understanding of bird song, a model system for animal communication and the neurobiology of learning, depends critically on making reliable, validated comparisons between the complex multidimensional syllables that are used in songs. However, most assessments of song similarity are based on human inspection of spectrograms, or computational methods developed from human intuitions. Using a novel automated operant conditioning system, we collected a large corpus of zebra finches’ ( Taeniopygia guttata ) decisions about song syllable similarity. We use this dataset to compare and externally validate similarity algorithms in widely-used publicly available software (Raven, Sound Analysis Pro, Luscinia). Although these methods all perform better than chance, they do not closely emulate the avian assessments. We then introduce a novel deep learning method that can produce perceptual similarity judgements trained on such avian decisions. We find that this new method outperforms the established methods in accuracy and more closely approaches the avian assessments. Inconsistent (hence ambiguous) decisions are a common occurrence in animal behavioural data; we show that a modification of the deep learning training that accommodates these leads to the strongest performance. We argue this approach is the best way to validate methods to compare song similarity, that our dataset can be used to validate novel methods, and that the general approach can easily be extended to other species.
Open AccessBird song comparison using deep learning trained from avian perceptual judgments
Our understanding of bird song, a model system for animal communication and the neurobiology of learning, depends critically on making reliable, validated comparisons between the complex multidimensional syllables that are used in songs. However, most assessments of song similarity are based on human inspection of spectrograms, or computational methods developed from human intuitions. Using a novel automated operant conditioning system, we collected a large corpus of zebra finches’ ( Taeniopygia guttata ) decisions about song syllable similarity. We use this dataset to compare and externally validate similarity algorithms in widely-used publicly available software (Raven, Sound Analysis Pro, Luscinia). Although these methods all perform better than chance, they do not closely emulate the avian assessments. We then introduce a novel deep learning method that can produce perceptual similarity judgements trained on such avian decisions. We find that this new method outperforms the established methods in accuracy and more closely approaches the avian assessments. Inconsistent (hence ambiguous) decisions are a common occurrence in animal behavioural data; we show that a modification of the deep learning training that accommodates these leads to the strongest performance. We argue this approach is the best way to validate methods to compare song similarity, that our dataset can be used to validate novel methods, and that the general approach can easily be extended to other species.
- Open Access
- 7 October 2019
- Published by PeerJ in PeerJ Computer Science
- Vol. 5, e223
NIPS4Bplus: a richly annotated birdsong audio dataset
Recent advances in birdsong detection and classification have approached a limit due to the lack of fully annotated recordings. In this paper, we present NIPS4Bplus, the first richly annotated birdsong audio dataset, that is comprised of recordings containing bird vocalisations along with their active species tags plus the temporal annotations acquired for them. Statistical information about the recordings, their species specific tags and their temporal annotations are presented along with example uses. NIPS4Bplus could be used in various ecoacoustic tasks, such as training models for bird population monitoring, species classification, birdsong vocalisation detection and classification.
- 7 October 2019
- Published by PeerJ in PeerJ Computer Science
- Vol. 5, e223
Open AccessNIPS4Bplus: a richly annotated birdsong audio dataset
Recent advances in birdsong detection and classification have approached a limit due to the lack of fully annotated recordings. In this paper, we present NIPS4Bplus, the first richly annotated birdsong audio dataset, that is comprised of recordings containing bird vocalisations along with their active species tags plus the temporal annotations acquired for them. Statistical information about the recordings, their species specific tags and their temporal annotations are presented along with example uses. NIPS4Bplus could be used in various ecoacoustic tasks, such as training models for bird population monitoring, species classification, birdsong vocalisation detection and classification.
- Open Access
Data-Efficient Weakly Supervised Learning for Low-Resource Audio Event Detection Using Deep Learning
We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are "weakly labelled" having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose a data-efficient training of a stacked convolutional and recurrent neural network. This neural network is trained in a multi instance learning setting for which we introduce a new loss function that leads to improved training compared to the usual approaches for weakly supervised learning. We successfully test our approach on two low-resource datasets that lack temporal labels.
Open AccessData-Efficient Weakly Supervised Learning for Low-Resource Audio Event Detection Using Deep Learning
We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are "weakly labelled" having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose a data-efficient training of a stacked convolutional and recurrent neural network. This neural network is trained in a multi instance learning setting for which we introduce a new loss function that leads to improved training compared to the usual approaches for weakly supervised learning. We successfully test our approach on two low-resource datasets that lack temporal labels.
- Open Access
- 18 August 2018
- Published by MDPI AG in Applied Sciences
- Vol. 8 (8) , 1397
Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets
In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.
- 18 August 2018
- Published by MDPI AG in Applied Sciences
- Vol. 8 (8) , 1397
Open AccessDeep Learning for Audio Event Detection and Tagging on Low-Resource Datasets
In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.
- 1 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 656-660
Deductive refinement of species labelling in weakly labelled birdsong recordings
Many approaches have been used in bird species classification from their sound in order to provide labels for the whole of a recording. However, a more precise classification of each bird vocalization would be of great importance to the use and management of sound archives and bird monitoring. In this work, we introduce a technique that using a two step process can first automatically detect all bird vocalizations and then, with the use of `weakly' labelled recordings, classify them. Evaluations of our proposed method show that it achieves a correct classification of 75.4% when used in a synthetic dataset.
- 1 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 656-660
Deductive refinement of species labelling in weakly labelled birdsong recordings
Many approaches have been used in bird species classification from their sound in order to provide labels for the whole of a recording. However, a more precise classification of each bird vocalization would be of great importance to the use and management of sound archives and bird monitoring. In this work, we introduce a technique that using a two step process can first automatically detect all bird vocalizations and then, with the use of `weakly' labelled recordings, classify them. Evaluations of our proposed method show that it achieves a correct classification of 75.4% when used in a synthetic dataset.
- Open Access
- 8 September 2016
- Published by International Speech Communication Association
- p. 2607-2611
Individual Identity in Songbirds: Signal Representations and Metric Learning for Locating the Information in Complex Corvid Calls
- 8 September 2016
- Published by International Speech Communication Association
- p. 2607-2611
Open AccessIndividual Identity in Songbirds: Signal Representations and Metric Learning for Locating the Information in Complex Corvid Calls
- Open Access
Individual identity in songbirds: signal representations and metric learning for locating the information in complex corvid calls
Bird calls range from simple tones to rich dynamic multi-harmonic structures. The more complex calls are very poorly understood at present, such as those of the scientifically important corvid family (jackdaws, crows, ravens, etc.). Individual birds can recognise familiar individuals from calls, but where in the signal is this identity encoded? We studied the question by applying a combination of feature representations to a dataset of jackdaw calls, including linear predictive coding (LPC) and adaptive discrete Fourier transform (aDFT). We demonstrate through a classification paradigm that we can strongly outperform a standard spectrogram representation for identifying individuals, and we apply metric learning to determine which time-frequency regions contribute most strongly to robust individual identification. Computational methods can help to direct our search for understanding of these complex biological signals.
Open AccessIndividual identity in songbirds: signal representations and metric learning for locating the information in complex corvid calls
Bird calls range from simple tones to rich dynamic multi-harmonic structures. The more complex calls are very poorly understood at present, such as those of the scientifically important corvid family (jackdaws, crows, ravens, etc.). Individual birds can recognise familiar individuals from calls, but where in the signal is this identity encoded? We studied the question by applying a combination of feature representations to a dataset of jackdaw calls, including linear predictive coding (LPC) and adaptive discrete Fourier transform (aDFT). We demonstrate through a classification paradigm that we can strongly outperform a standard spectrogram representation for identifying individuals, and we apply metric learning to determine which time-frequency regions contribute most strongly to robust individual identification. Computational methods can help to direct our search for understanding of these complex biological signals.
- Open Access
Deductive Refinement of Species Labelling in Weakly Labelled Birdsong Recordings
Many approaches have been used in bird species classification from their sound in order to provide labels for the whole of a recording. However, a more precise classification of each bird vocalization would be of great importance to the use and management of sound archives and bird monitoring. In this work, we introduce a technique that using a two step process can first automatically detect all bird vocalizations and then, with the use of 'weakly' labelled recordings, classify them. Evaluations of our proposed method show that it achieves a correct classification of 61% when used in a synthetic dataset, and up to 89% when the synthetic dataset only consists of vocalizations larger than 1000 pixels.
Open AccessDeductive Refinement of Species Labelling in Weakly Labelled Birdsong Recordings
Many approaches have been used in bird species classification from their sound in order to provide labels for the whole of a recording. However, a more precise classification of each bird vocalization would be of great importance to the use and management of sound archives and bird monitoring. In this work, we introduce a technique that using a two step process can first automatically detect all bird vocalizations and then, with the use of 'weakly' labelled recordings, classify them. Evaluations of our proposed method show that it achieves a correct classification of 61% when used in a synthetic dataset, and up to 89% when the synthetic dataset only consists of vocalizations larger than 1000 pixels.
- Open Access
- 20 July 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 23 (23299290) , 1
Speech Analysis and Synthesis with a Computationally Efficient Adaptive Harmonic Model
Harmonic models have to be both precise and fast in order to represent the speech signal adequately and be able to process large amount of data in a reasonable amount of time. For these purposes, the full-band adaptive harmonic model (aHM) used by the adaptive iterative refinement (AIR) algorithm has been proposed in order to accurately model the perceived characteristics of a speech signal. Even though aHM-AIR is precise, it lacks the computational efficiency that would make its use convenient for large databases. The least squares (LS) solution used in the original aHM-AIR accounts for most of the computational load. In a previous paper, we suggested a peak picking (PP) approach as a substitution to the LS solution. In order to integrate the adaptivity scheme of aHM in the PP approach, an adaptive discrete Fourier transform (aDFT), whose frequency basis can fully follow the variations of the f0 curve, was also proposed. In this paper, we complete the previous publication by evaluating the above methods for the whole analysis process of a speech signal. Evaluations have shown an average time reduction by four times using PP and aDFT compared to the LS solution. Additionally, based on formal listening tests, when using PP and aDFT, the quality of the re-synthesis is preserved compared to the original LS-based approach.
- 20 July 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 23 (23299290) , 1
Open AccessSpeech Analysis and Synthesis with a Computationally Efficient Adaptive Harmonic Model
Harmonic models have to be both precise and fast in order to represent the speech signal adequately and be able to process large amount of data in a reasonable amount of time. For these purposes, the full-band adaptive harmonic model (aHM) used by the adaptive iterative refinement (AIR) algorithm has been proposed in order to accurately model the perceived characteristics of a speech signal. Even though aHM-AIR is precise, it lacks the computational efficiency that would make its use convenient for large databases. The least squares (LS) solution used in the original aHM-AIR accounts for most of the computational load. In a previous paper, we suggested a peak picking (PP) approach as a substitution to the LS solution. In order to integrate the adaptivity scheme of aHM in the PP approach, an adaptive discrete Fourier transform (aDFT), whose frequency basis can fully follow the variations of the f0 curve, was also proposed. In this paper, we complete the previous publication by evaluating the above methods for the whole analysis process of a speech signal. Evaluations have shown an average time reduction by four times using PP and aDFT compared to the LS solution. Additionally, based on formal listening tests, when using PP and aDFT, the quality of the re-synthesis is preserved compared to the original LS-based approach.
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 1478-1482
A computationally efficient refinement of the fundamental frequency estimate for the Adaptive Harmonic Model
The full-band Adaptive Harmonic Model (aHM) can be used by the Adaptive Iterative Refinement (AIR) algorithm to accurately model the perceived characteristics of a speech recording. However, the Least Squares (LS) solution used in the current aHM-AIR makes the f 0 refinement in AIR time consuming, limiting the use of this algorithm for large databases. In this paper, a Peak Picking (PP) approach is suggested as a substitution to the LS solution. In order to integrate the adaptivity scheme of aHM in the PP approach, an adaptive Discrete Fourier Transform (aDFT) is also suggested in this paper, whose frequency basis can fully follow the frequency variations of the f 0 curve. Evaluations have shown an average time reduction of 5.5 times compared to the LS solution approach, while the quality of the resynthesis is preserved compared to the original aHM-AIR.
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 1478-1482
A computationally efficient refinement of the fundamental frequency estimate for the Adaptive Harmonic Model
The full-band Adaptive Harmonic Model (aHM) can be used by the Adaptive Iterative Refinement (AIR) algorithm to accurately model the perceived characteristics of a speech recording. However, the Least Squares (LS) solution used in the current aHM-AIR makes the f 0 refinement in AIR time consuming, limiting the use of this algorithm for large databases. In this paper, a Peak Picking (PP) approach is suggested as a substitution to the LS solution. In order to integrate the adaptivity scheme of aHM in the PP approach, an adaptive Discrete Fourier Transform (aDFT) is also suggested in this paper, whose frequency basis can fully follow the frequency variations of the f 0 curve. Evaluations have shown an average time reduction of 5.5 times compared to the LS solution approach, while the quality of the resynthesis is preserved compared to the original aHM-AIR.