From speech to letters - using a novel neural network architecture for grapheme based ASR.
Florian EybenMartin WöllmerBjörn W. SchullerAlex GravesPublished in: ASRU (2009)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- spontaneous speech
- broadcast news
- word recognition
- noisy environments
- speech corpus
- conversational speech
- hidden markov models
- cursive script
- speech processing
- spoken words
- recognition errors
- spoken language
- speaker identification
- speech synthesis
- language model
- recognition engine
- speech recognizer
- speaker recognition
- data sets
- speech recognizers
- endpoint detection
- hearing impaired
- speech retrieval
- speaker verification
- handwriting recognition
- non stationary
- natural language processing
- case study