204 citations · 344 across the 36 of their papers we have counts for
10 papers · 1 filter
DASHA: Diarization-Aware Speech-LLM ASR for Healthcare in Code-Switched Indic Doctor-Patient Conversations
Séverin Baroudi, Yanis Labrak, Shashi Kumar +7
Extracting patients' medical conditions from recorded primary-care conversations requires knowing who said what, which is difficult when speech is far-field, spontaneous, overlappi…
XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models
Shashi Kumar, Srikanth Madikeri, Juan Zuluaga-Gomez +5
Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretr…
Implementing contextual biasing in GPU decoder for online ASR
Iuliia Nigmatulina, Srikanth Madikeri, Esaú Villatoro-Tello +4
GPU decoding significantly accelerates the output of ASR predictions. While GPUs are already being used for online ASR decoding, post-processing and rescoring on GPUs have not been…
Lessons Learned in ATCO2: 5000 hours of Air Traffic Control Communications for Robust Automatic Speech Recognition and Understanding
Juan Zuluaga-Gomez, Iuliia Nigmatulina, Amrutha Prasad +8
Voice communication between air traffic controllers (ATCos) and pilots is critical for ensuring safe and efficient air traffic control (ATC). This task requires high levels of awar…
A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers
Juan Zuluaga-Gomez, Amrutha Prasad, Iuliia Nigmatulina +2
In this paper we propose a novel virtual simulation-pilot engine for speeding up air traffic controller (ATCo) training by integrating different state-of-the-art artificial intelli…
How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications
Juan Zuluaga-Gomez, Amrutha Prasad, Iuliia Nigmatulina +6
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…
BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications
Juan Zuluaga-Gomez, Seyyed Saeed Sarfjoo, Amrutha Prasad +5
Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract…
Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models
Srikanth Madikeri, Sibo Tong, Juan Zuluaga-Gomez +3
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 wrap…
Quantization of Acoustic Model Parameters in Automatic Speech Recognition Framework
Amrutha Prasad, Petr Motlicek, Srikanth Madikeri
State-of-the-art hybrid automatic speech recognition (ASR) system exploits deep neural network (DNN) based acoustic models (AM) trained with Lattice Free-Maximum Mutual Information…
Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition
Subhadeep Dey, Petr Motlicek, Trung Bui +1
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves tra…