MAESTRO: Matched Speech Text Representations through Modality Matching.
Zhehuai ChenYu ZhangAndrew RosenbergBhuvana RamabhadranPedro J. MorenoAnkur BapnaHeiga ZenPublished in: INTERSPEECH (2022)
Keyphrases
- text to speech synthesis
- text to speech
- string matching
- multi modal
- text recognition
- text input
- lexical features
- information retrieval
- spontaneous speech
- pattern matching
- multi lingual
- english text
- keywords
- text mining
- medical images
- text documents
- conversational speech
- matching algorithm
- graph matching
- web documents
- speech recognition
- audio visual
- text retrieval
- approximate pattern matching
- semantic matching
- semantic representations
- speech synthesis
- feature points
- free text
- text data
- object recognition
- language generation
- automatically discovering
- shape matching
- dialogue system
- speech signal
- image matching
- document analysis