Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition.
Adrien DufrauxEmmanuel VincentAwni HannunArmelle BrunMatthijs DouzePublished in: CoRR (2019)
Keyphrases
- speech recognition
- noisy environments
- automatic speech recognition
- hidden markov models
- speech signal
- language model
- speech synthesis
- speech processing
- speaker identification
- speech understanding
- speech recognition systems
- speech recognition technology
- speech recognizer
- handwriting recognition
- acoustic models
- speech retrieval
- pattern recognition
- broadcast news
- keyword spotting
- neural network
- spontaneous speech
- speaker recognition
- speaker adaptation
- speech recognition errors
- noise reduction
- noisy speech
- speech recognizers