arXiv subjects

Juan Zuluaga-Gomez

Publications and source records attributed to Juan Zuluaga-Gomez.

27 records · Page 2Linked to original sources

arXiv2022

BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications

Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract ATC named entities, e.g., aircraft callsigns. One common challenge is speech activity detection (SAD) and speaker diarization (SD). In the failure condition, two or more segments remain in the same recording, jeopardizing the overall performance. We propose a system that combines SAD and a BERT model to perform speaker change detection and speaker role detection (SRD) by chunking ASR transcripts, i.e., SD with a defined number of speakers together with SRD. The proposed model is evaluated on real-life public ATC databases. Our BERT SD model baseline reaches up to 10% and 20% token-based Jaccard error rate (JER) in public and private ATC databases. We also achieved relative improvements of 32% and 7.7% in JERs and SD error rate (DER), respectively, compared to VBx, a well-known SD system.

eess.AS↗

arXiv2022

IDIAPers @ Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach

In this paper, we describe our participation in the subtask 1 of CASE-2022, Event Causality Identification with Casual News Corpus. We address the Causal Relation Identification (CRI) task by exploiting a set of simple yet complementary techniques for fine-tuning language models (LMs) on a small number of annotated examples (i.e., a few-shot configuration). We follow a prompt-based prediction approach for fine-tuning LMs in which the CRI task is treated as a masked language modeling problem (MLM). This approach allows LMs natively pre-trained on MLM problems to directly generate textual responses to CRI-specific prompts. We compare the performance of this method against ensemble techniques trained on the entire dataset. Our best-performing submission was fine-tuned with only 256 instances per class, 15.7% of the all available data, and yet obtained the second-best precision (0.82), third-best accuracy (0.82), and an F1-score (0.85) very close to what was reported by the winner team (0.86).

cs.CL↗

arXiv2022

A two-step approach to leverage contextual data: speech recognition in air-traffic communications

Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR application can lead to a lower number of incidents caused by misunderstanding and improve air traffic management (ATM) efficiency. Evidently, high accuracy predictions, especially, of key information, i.e., callsigns and commands, are required to minimize the risk of errors. We prove that combining the benefits of ASR and Natural Language Processing (NLP) methods to make use of surveillance data (i.e. additional modality) helps to considerably improve the recognition of callsigns (named entity). In this paper, we investigate a two-step callsign boosting approach: (1) at the 1 step (ASR), weights of probable callsign n-grams are reduced in G.fst and/or in the decoding FST (lattices), (2) at the 2 step (NLP), callsigns extracted from the improved recognition outputs with Named Entity Recognition (NER) are correlated with the surveillance data to select the most suitable one. Boosting callsign n-grams with the combination of ASR and NLP methods eventually leads up to 53.7% of an absolute, or 60.4% of a relative, improvement in callsign recognition.

cs.CL↗

arXiv2022

A Survey of Breast Cancer Screening Techniques: Thermography and Electrical Impedance Tomography

Breast cancer is a disease that threatens many women's life, thus, early and accurate detection plays a key role in reducing the mortality rate. Mammography stands as the reference technique for breast cancer screening; nevertheless, many countries still lack access to mammograms due to economic, social, and cultural issues. Last advances in computational tools, infrared cameras, and devices for bio-impedance quantification allowed the development of parallel techniques like thermography, infrared imaging, and electrical impedance tomography, these being faster, reliable and cheaper. In the last decades, these have been considered as complement procedures for breast cancer diagnosis, where many studies concluded that false positive and false negative rates are greatly reduced. This work aims to review the last breakthroughs about the three above-mentioned techniques describing the benefits of mixing several computational skills to obtain a better global performance. In addition, we provide a comparison between several machine learning techniques applied to breast cancer diagnosis going from logistic regression, decision trees, and random forest to artificial, deep, and convolutional neural networks. Finally, it is mentioned several recommendations for 3D breast simulations, pre-processing techniques, biomedical devices in the research field, prediction of tumor location and size.

eess.IV↗

arXiv2021

Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems

Air traffic management and specifically air-traffic control (ATC) rely mostly on voice communications between Air Traffic Controllers (ATCos) and pilots. In most cases, these voice communications follow a well-defined grammar that could be leveraged in Automatic Speech Recognition (ASR) technologies. The callsign used to address an airplane is an essential part of all ATCo-pilot communications. We propose a two-steps approach to add contextual knowledge during semi-supervised training to reduce the ASR system error rates at recognizing the part of the utterance that contains the callsign. Initially, we represent in a WFST the contextual knowledge (i.e. air-surveillance data) of an ATCo-pilot communication. Then, during Semi-Supervised Learning (SSL) the contextual knowledge is added by second-pass decoding (i.e. lattice re-scoring). Results show that `unseen domains' (e.g. data from airports not present in the supervised training data) are further aided by contextual SSL when compared to standalone SSL. For this task, we introduce the Callsign Word Error Rate (CA-WER) as an evaluation metric, which only assesses ASR performance of the spoken callsign in an utterance. We obtained a 32.1% CA-WER relative improvement applying SSL with an additional 17.5% CA-WER improvement by adding contextual knowledge during SSL on a challenging ATC-based test set gathered from LiveATC.

cs.CL↗

arXiv2021

Improving callsign recognition with air-surveillance data in air-traffic communication

Automatic Speech Recognition (ASR) can be used as the assistance of speech communication between pilots and air-traffic controllers. Its application can significantly reduce the complexity of the task and increase the reliability of transmitted information. Evidently, high accuracy predictions are needed to minimize the risk of errors. Especially, high accuracy is required in recognition of key information, such as commands and callsigns, used to navigate pilots. Our results prove that the surveillance data containing callsigns can help to considerably improve the recognition of a callsign in an utterance when the weights of probable callsign n-grams are reduced per utterance. In this paper, we investigate two approaches: (1) G-boosting, when callsigns weights are adjusted at language model level (G) and followed by the dynamic decoder with an on-the-fly composition, and (2) lattice rescoring when callsign information is introduced on top of lattices generated using a conventional decoder. Boosting callsign n-grams with the combination of two methods allowed us to gain 28.4% of absolute improvement in callsign recognition accuracy and up to 74.2% of relative improvement in WER of callsign recognition.

cs.CL↗

arXiv2020

Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models

We present a simple wrapper that is useful to train acoustic models in PyTorch using Kaldi's LF-MMI training framework. The wrapper, called pkwrap (short form of PyTorch kaldi wrapper), enables the user to utilize the flexibility provided by PyTorch in designing model architectures. It exposes the LF-MMI cost function as an autograd function. Other capabilities of Kaldi have also been ported to PyTorch. This includes the parallel training ability when multi-GPU environments are unavailable and decode with graphs created in Kaldi. The package is available on Github at https://github.com/idiap/pkwrap.

eess.AS↗

arXiv2020

Automatic Speech Recognition Benchmark for Air-Traffic Communications

Advances in Automatic Speech Recognition (ASR) over the last decade opened new areas of speech-based automation such as in Air-Traffic Control (ATC) environment. Currently, voice communication and data links communications are the only way of contact between pilots and Air-Traffic Controllers (ATCo), where the former is the most widely used and the latter is a non-spoken method mandatory for oceanic messages and limited for some domestic issues. ASR systems on ATCo environments inherit increasing complexity due to accents from non-English speakers, cockpit noise, speaker-dependent biases, and small in-domain ATC databases for training. Hereby, we introduce CleanSky EC-H2020 ATCO2, a project that aims to develop an ASR-based platform to collect, organize and automatically pre-process ATCo speech-data from air space. This paper conveys an exploratory benchmark of several state-of-the-art ASR models trained on more than 170 hours of ATCo speech-data. We demonstrate that the cross-accent flaws due to speakers' accents are minimized due to the amount of data, making the system feasible for ATC environments. The developed ASR system achieves an averaged word error rate (WER) of 7.75% across four databases. An additional 35% relative improvement in WER is achieved on one test set when training a TDNNF system with byte-pair encoding.

cs.CL↗

arXiv2019

A CNN-based methodology for breast cancer diagnosis using thermal images

Micro Abstract: A recent study from GLOBOCAN disclosed that during 2018 two million women worldwide had been diagnosed from breast cancer. This study presents a computer-aided diagnosis system based on convolutional neural networks as an alternative diagnosis methodology for breast cancer diagnosis with thermal images. Experimental results showed that lower false-positives and false-negatives classification rates are obtained when data pre-processing and data augmentation techniques are implemented in these thermal images. Background: There are many types of breast cancer screening techniques such as, mammography, magnetic resonance imaging, ultrasound and blood sample tests, which require either, expensive devices or personal qualified. Currently, some countries still lack access to these main screening techniques due to economic, social or cultural issues. The objective of this study is to demonstrate that computer-aided diagnosis(CAD) systems based on convolutional neural networks (CNN) are faster, reliable and robust than other techniques. Methods: We performed a study of the influence of data pre-processing, data augmentation and database size versus a proposed set of CNN models. Furthermore, we developed a CNN hyper-parameters fine-tuning optimization algorithm using a tree parzen estimator. Results: Among the 57 patients database, our CNN models obtained a higher accuracy (92\%) and F1-score (92\%) that outperforms several state-of-the-art architectures such as ResNet50, SeResNet50 and Inception. Also, we demonstrated that a CNN model that implements data-augmentation techniques reach identical performance metrics in comparison with a CNN that uses a database up to 50\% bigger. Conclusion: This study highlights the benefits of data augmentation and CNNs in thermal breast images. Also, it measures the influence of the database size in the performance of CNNs.

cs.CV↗