Preparing Audio Recordings of Everyday Speech for Prosody Research: The Case of the ORD Corpus.

Tatiana Y. Sherstinova

Published in: SPECOM (2017)

Keyphrases

audio recordings
text to speech
music information retrieval
speech synthesis
speech recognition
audio visual
multi stream
multi modal
prosodic features
hidden markov models
low level
natural language processing
lexical features
conversational speech