Conformer-Based Target-Speaker Automatic Speech Recognition For Single-Channel Audio.
Yang ZhangKrishna C. PuvvadaVitaly LavrukhinBoris GinsburgPublished in: ICASSP (2023)
Keyphrases
- automatic speech recognition
- single channel
- broadcast news
- speech recognition
- multi channel
- acoustic features
- speech signal
- speaker identification
- speech enhancement
- hidden markov models
- noisy environments
- signal processing
- frequency domain
- spontaneous speech
- multimedia
- conversational speech
- wavelet decomposition
- independent component analysis
- speech retrieval
- spoken document retrieval
- speaker diarization
- speaker verification
- audio stream
- sound source
- prior information
- visual information
- information retrieval