SPEED: Open-Source Framework to Accelerate Speech Recognition on Embedded GPUs.
Syed Mohammad Asad Hassan JafriAhmed HemaniLeonardo IntesaPublished in: DSD (2017)
Keyphrases
- speech recognition
- open source
- hidden markov models
- language model
- speech understanding
- speech signal
- speech processing
- speech recognizer
- speech synthesis
- information retrieval
- speaker identification
- automatic speech recognition
- machine learning
- speech recognition systems
- acoustic models
- speech recognition errors
- speech recognizers