Universal speaker recognition encoders for different speech segments duration.
Sergey NovoselovVladimir VolokhovGalina LavrentyevaPublished in: CoRR (2022)
Keyphrases
- speaker recognition
- speech segments
- automatic speech recognition
- gaussian mixture model
- speech signal
- speech recognition
- speech retrieval
- feature vectors
- speaker identification
- vector quantization
- speaker verification
- probabilistic neural network
- broadcast news
- audio stream
- emotional speech
- noisy environments
- speaker diarization
- feature extraction
- image segmentation
- human computer interaction
- mel frequency cepstral coefficients
- maximum likelihood
- hidden markov models
- artificial neural networks