Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition.
Sunit SivasankaranEmmanuel VincentDominique FohrPublished in: EUSIPCO (2020)
Keyphrases
- automatic speech recognition
- speech recognition
- recognition errors
- speech signal
- word error rate
- hidden markov models
- broadcast news
- conversational speech
- noisy environments
- speech sounds
- spoken words
- acoustic features
- speech corpus
- speech retrieval
- spontaneous speech
- speech segments
- vocal tract
- speech recognizers
- acoustic models
- speaker dependent
- formant frequencies
- speaker independent
- sound source
- word recognition
- machine learning
- speech recognition systems
- speech recognizer
- speech synthesis
- speaker identification
- linear prediction