4 papers
Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data
Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang +2
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we…
Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval
Yi-Chen Chen, Sung-Feng Huang, Chia-Hao Shen +2
Word embedding or Word2Vec has been successful in offering semantics for text words learned from the context of words. Audio Word2Vec was shown to offer phonetic structures for spo…
Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang +1
Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods ca…
Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencoder
Yu-An Chung, Chao-Chung Wu, Chia-Hao Shen +2
The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the…