paper-with-me

Papers

Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model

2024-02-08 · Hung-Chieh Fang, Nai-Xuan Ye, Yi-Jen Shih, Puyuan Peng, Hsuan-Fu Wang, Layne Berry, Hung-Yi Lee, David Harwath

Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language understanding tasks that require semantic comprehension. Existing works often rely on additional speech-text data as intermediate targets, which is costly in the real-world setting. To address this challenge, we propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process, where the targets are derived from a visually-ground speech model, notably eliminating the need for speech-text paired data. Our experimental results on four spoken language understanding (SLU) benchmarks suggest the superiority of our model in capturing semantic information.

📄 PDF Abstract BibTeX arXiv:2402.05819

Code (0)

등록된 구현이 없습니다.

Tasks

modelSpoken Language Understanding

Similar Papers 제목 키워드 기반

Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages

2022-05-02 · Felix Wu, Kwangyoun Kim, Shinji Watanabe, Kyu Han 외

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervise…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decodernamed-entity-recognition+7

Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels

2023-03-30 · Tzeviya Sylvia Fuchs, Yedid Hoshen

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective …

Pseudo LabelSegmentation

Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition

2023-05-19 · Siyuan Feng, Ming Tu, Rui Xia, Chuanzeng Huang 외

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo…

DiversitySelf-Supervised Learningspeech-recognitionSpeech Recognition

Pseudo Label Is Better Than Human Label

2022-03-22 · Dongseong Hwang, Khe Chai Sim, Zhouyuan Huo, Trevor Strohman

State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data. Human transcription is expensive and time consuming. Factors such as the quality and consist…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Pseudo Labelspeech-recognition+1

Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification

2021-04-05 · Aswin Sivaraman, Sunwoo Kim, Minje Kim

Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy …

Data AugmentationDenoisingPrivacy PreservingSelf-Supervised Learning+1