Lrspeech: Extremely low-resource speech synthesis and recognition
Speech synthesis (text to speech, TTS) and recognition (automatic speech recognition, ASR)
are important speech tasks, and require a large amount of text and speech pairs for model …
are important speech tasks, and require a large amount of text and speech pairs for model …
Almost unsupervised text to speech and automatic speech recognition
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 …
processing and both achieve impressive performance thanks to the recent advance in deep …
Unsupervised cross-modal alignment of speech and text embedding spaces
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 …
different languages can be aligned without any parallel data supervision. Inspired by the …
Unsupervised speech recognition via segmental empirical output distribution matching
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 …
data, under the assumption that the learner can only access to the input utterances and a …
Phonetic-and-semantic embedding of spoken words with applications in spoken content retrieval
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 …
learned from the context of words. Audio Word2Vec was shown to offer phonetic structures …
Iterative pseudo-forced alignment by acoustic ctc loss for self-supervised asr domain adaptation
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 …
work, we propose a self-supervised domain adaptation method, based upon an iterative …
Improving word recognition in speech transcriptions by decision-level fusion of stemming and two-way phoneme pruning
We introduce an unsupervised approach for correcting highly imperfect speech
transcriptions based on a decision-level fusion of stemming and two-way phoneme pruning …
transcriptions based on a decision-level fusion of stemming and two-way phoneme pruning …
Almost-unsupervised speech recognition with close-to-zero resource based on phonetic structures learned from very small unpaired speech and text data
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 …
difficult for more than 95% of languages all over the world which are low-resourced …
Learning decision making strategies of non-experts: A next-gail model for taxi drivers
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 …
spatial-temporal data (HSTD) are generated from the urban areas, eg, passenger-seeking …
Temporally aligning long audio interviews with questions: a case study in multimodal data integration
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 …
complete supervision during training. However, this is typically not in the context of long …