Personalizing Speech Start Point and End Point Detection in ASR Systems from Speaker Embeddings.
Aditya JayasimhaPeriyasamy ParamasivamPublished in: SLT (2021)
Keyphrases
- automatic speech recognition
- speech recognition
- endpoints
- noisy environments
- speech signal
- automatic speech recognition systems
- speech recognizers
- speaker verification
- audio visual
- object detection
- hidden markov models
- speech synthesis
- detection algorithm
- false positives
- vector space
- automatic transcription
- spontaneous speech
- feature extraction
- non stationary
- speaker dependent
- conversational speech
- speaker recognition
- speaker identification
- broadcast news
- web search
- dimensionality reduction
- noise reduction