Towards Visually Grounded Sub-Word Speech Unit Discovery.
David HarwathJames R. GlassPublished in: CoRR (2019)
Keyphrases
- speech recognition
- speech recognizer
- speech recognition systems
- recognition errors
- lexical features
- spoken document retrieval
- english text
- spontaneous speech
- prosodic features
- text input
- spoken language
- automatic speech recognition
- spoken documents
- speech signal
- speech synthesis
- word error rate
- knowledge discovery
- keyword spotting
- automatic transcription
- co occurrence
- broadcast news
- word recognition
- scientific discovery
- discovery process
- audio visual
- speech recognizers
- n gram
- spoken term detection
- text to speech
- grapheme to phoneme conversion
- hidden markov models
- vocal tract
- multimodal interfaces
- keywords
- related words
- linguistic knowledge
- dialogue system
- pattern discovery
- speech sounds
- human computer interaction
- pattern recognition