Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0
acoustic model

Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model

Interspeech (Interspeech), 2021

6 April 2021

ArXiv (abs)PDF HTML

Papers citing "Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model"

6 / 6 papers shown

Title
DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model Yanzhe Fu Yueteng Kang Songjun Cao Long Ma 161 12 0 16 Mar 2023
Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasksIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 Esaú Villatoro-Tello S. Madikeri Juan Pablo Zuluaga Bidisha Sharma Seyyed Saeed Sarfjoo Iuliia Nigmatulina P. Motlícek A. Ivanov A. Ganapathiraju 147 3 0 16 Dec 2022
Are disentangled representations all you need to build speaker anonymization systems?Interspeech (Interspeech), 2022 Pierre Champion D. Jouvet Anthony Larcher 249 33 0 22 Aug 2022
Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training Mitchell DeHaven J. Billa VLM AI4TS 120 10 0 01 Jul 2022
Boosting Cross-Domain Speech Recognition with Self-SupervisionIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2022 Hanjing Zhu Gaofeng Cheng Yongfeng Zhang Wenxin Hou Pengyuan Zhang Yonghong Yan 306 22 0 20 Jun 2022
How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control CommunicationsSpoken Language Technology Workshop (SLT), 2022 Juan Pablo Zuluaga Amrutha Prasad Iuliia Nigmatulina Seyyed Saeed Sarfjoo P. Motlícek Matthias Kleinert H. Helmke Oliver Ohneiser Qingran Zhan 236 52 0 31 Mar 2022