Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep …
Recent research has shown that word embedding spaces learned from text corpora of different languages can be aligned without any parallel data supervision. Inspired by the …
We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a …
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 …
High-quality data labeling from specific domains is costly and human time-consuming. In this work, we propose a self-supervised domain adaptation method, based upon an iterative …
S Mehra, S Susan - … Computing: 10th International Conference, IACC 2020 …, 2021 - Springer
We introduce an unsupervised approach for correcting highly imperfect speech transcriptions based on a decision-level fusion of stemming and two-way phoneme pruning …
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 …
Thanks to the rapid development of mobile sensing techniques, massive human-generated spatial-temporal data (HSTD) are generated from the urban areas, eg, passenger-seeking …
The problem of audio-to-text alignment has seen significant amount of research using complete supervision during training. However, this is typically not in the context of long …