Using x-grams for speech-to-speech translation.
Adrià de GispertJosé B. MariñoPublished in: INTERSPEECH (2002)
Keyphrases
- speech recognition
- speech signal
- broadcast news
- audio visual
- real time
- spoken language
- endpoint detection
- recognition engine
- emotion recognition
- spontaneous speech
- vocal tract
- hidden markov models
- automatic speech recognition
- speaker identification
- speech synthesis
- speech processing
- speech recognizer
- text to speech synthesis
- automatic speech recognition systems
- multi stream
- speaker recognition
- language acquisition
- machine translation
- n gram
- natural language processing
- probabilistic model
- feature vectors
- search engine