Papers

Contextual Learning for Missing Speech Automatic Speech Recognition

International Conference
2021~
작성자
dsp
작성일
2024-01-22 16:15
조회
1704
Authors : Yeona Hong, Miseul Kim, Woo-Jin Chung, Hong-Goo Kang

Year : 2024

Publisher / Conference : International Conference on Electronics, Information, and Communication (ICEIC)

Research area : Speech Signal Processing, Speech Recognition

Presentation/Publication date : 2024.01.29

Presentation : Poster

—In this paper, we present an automatic speech recognition (ASR) system that is capable of decoding complete transcriptions from speech even in cases where there are missing segments in the audio. To predict complete transcriptions from speech that may have missing segments, we utilize a contextual learning approach inspired by recent language model training approaches, in which our model leverages surrounding speech segments as cues for the prediction. Our model consists of two modules: a contextual feature extractor designed with the structure of wav2vec 2.0, and a projection layer. We further explore various masking lengths for model training so as to optimally benefit the ASR system without compromising its performance. Our proposed methodology demonstrates highquality ASR performance on missing speech segments of various lengths, ranging from a word error rate (WER) of 4.7% on 0.25 seconds segments to 18.5% on 1 second segments.
전체 368
150 International Conference Yeona Hong, Miseul Kim, Woo-Jin Chung, Hong-Goo Kang "Contextual Learning for Missing Speech Automatic Speech Recognition" in International Conference on Electronics, Information, and Communication (ICEIC), 2024
149 International Conference Juhwan Yoon, Seyun Um, Woo-Jin Chung, Hong-Goo Kang "SC-ERM: Speaker-Centric Learning for Speech Emotion Recognition" in International Conference on Electronics, Information, and Communication (ICEIC), 2024
148 International Conference Hejung Yang, Hong-Goo Kang "On Fine-Tuning Pre-Trained Speech Models With EMA-Target Self-Supervised Loss" in ICASSP, 2024
147 International Conference Hong-Goo Kang, W. Bastiaan Kleijn, Jan Skoglund, Michael Chinen "Convolutional Transformer for Neural Speech Coding" in Audio Engineering Society Convention, 2023
146 International Conference Hong-Goo Kang, Jan Skoglund, W. Bastiaan Kleijn, Andrew Storus, Hengchin Yeh "A High-Rate Extension to Soundstream" in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2023
145 International Conference Zhenyu Piao, Hyungseob Lim, Miseul Kim, Hong-goo Kang "PDF-NET: Pitch-adaptive Dynamic Filter Network for Intra-gender Speaker Verification" in APSIPA ASC, 2023
144 International Conference WooSeok Ko, Seyun Um, Zhenyu Piao, Hong-goo Kang "Consideration of Varying Training Lengths for Short-Duration Speaker Verification" in APSIPA ASC, 2023
143 International Conference Miseul Kim, Zhenyu Piao, Jihyun Lee, Hong-Goo Kang "BrainTalker: Low-Resource Brain-to-Speech Synthesis with Transfer Learning using Wav2Vec 2.0" in The IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2023
142 International Conference Seyun Um, Jihyun Kim, Jihyun Lee, Hong-Goo Kang "Facetron: A Multi-speaker Face-to-Speech Model based on Cross-Modal Latent Representations" in EUSIPCO, 2023
141 International Conference Hejung Yang, Hong-Goo Kang "Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement" in INTERSPEECH, 2023