Search Results for author:
Found 53 papers, 22 papers with code
Team Innovators at SemEval-2022 for Task 8: Multi-Task Training with Hyperpartisan and Semantic Relation for Multi-Lingual News Article Similarity
This work represents the system proposed by team Innovators for SemEval 2022 Task 8: Multilingual News Article Similarity.
NLPHut’s Participation at WAT2021
Our submission tops in English→Malayalam Multimodal translation task (text-only translation, and Malayalam caption), and ranks second-best in English→Hindi Multimodal translation task (text-only translation, and Hindi caption).
IDIAP Submission@LT-EDI-ACL2022: Homophobia/Transphobia Detection in social media comments
The increased expansion of abusive content on social media platforms negatively affects online users.
IDIAP Submission@LT-EDI-ACL2022: Detecting Signs of Depression from Social Media Text
Given social media postings in English, the submitted system classify the signs of depression into three labels, namely “not depressed,” “moderately depressed,” and “severely depressed.” Our best model is ranked 3^{rd} position with 0. 54% accuracy .
Hierarchical Multi-task learning framework for Isometric-Speech Language Translation
In this paper, we propose a hierarchical approach to generate isometric translation on MUST-C dataset, we achieve a BERTscore of 0. 85, a length ratio of 1. 087, a BLEU score of 42. 3, and a length range of 51. 03%.
Investigating Cross-lingual Multi-level Adaptive Networks: The Importance of the Correlation of Source and Target Languages
We experiment with three different scenarios using, i) French, as a source language uncorrelated to the target language, ii) Ukrainian, as a source language correlated to the target one and finally iii) English as a source language uncorrelated to the target language using a relatively large amount of data in respect to the other two scenarios.
ODIANLP’s Participation in WAT2020
We have participated in the English-Hindi Multimodal task and Indic task.
IDIAP_TIET@LT-EDI-ACL2022 : Hope Speech Detection in Social Media using Contextualized BERT with Attention Mechanism
With the increase of users on social media platforms, manipulating or provoking masses of people has become a piece of cake.
Legal and Ethical Challenges in Recording Air Traffic Control Speech
In this paper the authors detail the various legal and ethical issues faced during the ATCO2 project.
Automatic Summarization for Creative Writing: BART based Pipeline Method for Generating Summary of Movie Scripts
This paper documents our approach for the Creative-Summ 2022 shared task for Automatic Summarization of Creative Writing.
BertAA : BERT fine-tuning for Authorship Attribution
Identifying the author of a given text can be useful in historical literature, plagiarism detection, or police investigations.
Detection of Similar Languages and Dialects Using Deep Supervised Autoencoder
Language detection is considered a difficult task especially for similar languages, varieties, and dialects.
Open Machine Translation for Low Resource South American Languages (AmericasNLP 2021 Shared Task Contribution)
This paper describes the team (“Tamalli”)’s submission to AmericasNLP2021 shared task on Open Machine Translation for low resource South American languages.
Multimodal Neural Machine Translation System for English to Bengali
Multimodal Machine Translation (MMT) systems utilize additional information from other modalities beyond text to improve the quality of machine translation (MT).
IDIAP Submission@LT-EDI-ACL2022 : Hope Speech Detection for Equality, Diversity and Inclusion
It reflects the belief to achieve an objective, discovers a new path, or become motivated to formulate pathways. In this paper we classify given a social media post, hope speech or not hope speech, using ensembled voting of BERT, ERNIE 2. 0 and RoBERTa for English language with 0. 54 macro F1-score (2^{st} rank).
A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport
Based on the SOTD, we propose Optimal Temporal Transport Classification (OTTC) loss for ASR and contrast its behavior with CTC.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
Recent research has demonstrated that training a linear connector between speech foundation encoders and large language models (LLMs) enables this architecture to achieve strong ASR capabilities.
Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction
Efficiently deriving structured workflows from unannotated dialogs remains an underexplored and formidable challenge in computational linguistics.
Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions
Our experiments, targeting two challenging bias descriptors, factual reporting and political bias, showed a significant performance improvement at the source media level.
Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper
The training of automatic speech recognition (ASR) with little to no supervised data remains an open question.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
LM-assisted keyword biasing with Aho-Corasick algorithm for Transducer-based ASR
The language model is used as an additional support to keyword biasing when the language model is combined with bias entities in a single context graph to take care of the overall performance.
TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR
In addition to ASR, we conduct experiments on 3 different tasks: speaker change detection, endpointing, and NER.
XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models
Our experiments on the AMI dataset reveal that the XLSR-Transducer achieves 4% absolute WER improvement over Whisper large-v2 and 8% over a Zipformer transducer model trained from scratch.
DAIC-WOZ: On the Validity of Using the Therapist's prompts in Automatic Depression Detection from Clinical Interviews
Finally, to highlight the magnitude of this bias, we achieve a 0. 90 F1 score by intentionally exploiting it, the highest result reported to date on this dataset using only textual information.
Reliability Estimation of News Media Sources: Birds of a Feather Flock Together
Contrary to previous research, our proposed approach models the problem as the estimation of a reliability degree, and not a reliability label, based on how all the news media sources interact with each other on the Web.
Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews
We propose a simple approach for weighting self-connecting edges in a Graph Convolutional Network (GCN) and show its impact on depression detection from transcribed clinical interviews.
HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition
In particular, multi-head HyperConformer achieves comparable or higher recognition performance while being more efficient than Conformer in terms of inference speed, memory, parameter count, and available training data.
Lessons Learned in ATCO2: 5000 hours of Air Traffic Control Communications for Robust Automatic Speech Recognition and Understanding
This paper explores the lessons learned from the ATCO2 project, a project that aimed to develop a unique platform to collect and preprocess large amounts of ATC data from airspace in real time.
A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers
The overall pipeline is composed of the following submodules: (i) automatic speech recognition (ASR) system that transforms audio into a sequence of words; (ii) high-level air traffic control (ATC) related entity parser that understands the transcribed voice communication; and (iii) a text-to-speech submodule that generates a spoken utterance that resembles a pilot based on the situation of the dialogue.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks
In this paper, we perform an exhaustive evaluation of different representations to address the intent classification problem in a Spoken Language Understanding (SLU) setup.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Speech and Natural Language Processing Technologies for Pseudo-Pilot Simulator
The system understands the voice communications issued by the ATCo, and, in turn, it generates a spoken prompt that follows the pilot's phraseology to the initial communication.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications
In this paper, we introduce the ATCO2 corpus, a dataset that aims at fostering research on the challenging ATC field, which has lagged behind due to lack of annotated data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
IDIAPers @ Causal News Corpus 2022: Extracting Cause-Effect-Signal Triplets via Pre-trained Autoregressive Language Model
In this paper, we describe our shared task submissions for Subtask 2 in CASE-2022, Event Causality Identification with Casual News Corpus.
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.
Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Prediction
We propose to disentangle the per-evidence relevance probability and its contribution to the final veracity probability in an interpretable way -- the final veracity probability is proportional to a linear ensemble of per-evidence relevance probabilities.
How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications
Recent work on self-supervised pre-training focus on leveraging large-scale unlabeled speech data to build robust end-to-end (E2E) acoustic models (AM) that can be later fine-tuned on downstream tasks e. g., automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications
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.
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Grammar Based Speaker Role Identification for Air Traffic Control Speech Recognition
In this work, we propose to (1) automatically segment the ATCO and pilot data based on an intuitive approach exploiting ASR transcripts and (2) subsequently consider an automatic recognition of ATCOs' and pilots' voice as two separate tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Comparison of Methods for OOV-word Recognition on a New Public Dataset
A common problem for automatic speech recognition systems is how to recognize words that they did not see during training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
IEEE SLT 2021 Alpha-mini Speech Challenge: Open Datasets, Tracks, Rules and Baselines
In this challenge, we open source a sizable speech, keyword, echo and noise corpus for promoting data-driven methods, particularly deep-learning approaches on KWS and SSL.
Sound Audio and Speech Processing
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.
Audio and Speech Processing Sound
Automatic Speech Recognition Benchmark for Air-Traffic Communications
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
OdiEnCorp 2.0: Odia-English Parallel Corpus for Machine Translation
The preparation of parallel corpora is a challenging task, particularly for languages that suffer from under-representation in the digital world.
Abstract Text Summarization: A Low Resource Challenge
We propose an iterative data augmentation approach which uses synthetic data along with the real summarization data for the German language.
Idiap NMT System for WAT 2019 Multimodal Translation Task
This paper describes the Idiap submission to WAT 2019 for the English-Hindi Multi-Modal Translation Task.
MuMMER: Socially Intelligent Human-Robot Interaction in Public Spaces
In the EU-funded MuMMER project, we have developed a social robot designed to interact naturally and flexibly with users in public spaces such as a shopping mall.
Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Deep Neural Networks for Multiple Speaker Detection and Localization
We propose to use neural networks for simultaneous detection and localization of multiple sound sources in human-robot interaction.
The DBOX Corpus Collection of Spoken Human-Human and Human-Machine Dialogues
We first start with human-human Wizard of Oz experiments to collect human-human data in order to model natural human dialogue behaviour, for better understanding of phenomena of human interactions and predicting interlocutors actions, and then replace the human Wizard by an increasingly advanced dialogue system, using evaluation data for system improvement.
