Indic TIMIT and Indic English lexicon: A speech database of Indian speakers using TIMIT stimuli and a lexicon from their mispronunciations.
Chiranjeevi YarraRitu AggarwalAvni RajpalPrasanta Kumar GhoshPublished in: O-COCOSDA (2019)
Keyphrases
- speech corpus
- speaker verification
- database
- speech recognition
- natural language
- hidden markov models
- automatic speech recognition
- word recognition
- databases
- domain specific
- acoustic features
- relational databases
- language identification
- environmental sounds
- speech synthesis
- audio visual
- database systems
- noisy environments
- machine translation
- handwritten words
- broadcast news
- english language
- speaker dependent
- query language
- speech signal
- bilingual lexicon
- spoken document retrieval
- natural language processing
- machine readable dictionaries
- english text
- text to speech
- spoken language
- speaker identification
- lexical knowledge
- linguistic knowledge
- information retrieval
- cross language
- information extraction