But System for the Second Dihard Speech Diarization Challenge.
Federico LandiniShuai WangMireia DíezLukás BurgetPavel MatejkaKaterina ZmolíkováLadislav MosnerAnna SilnovaOldrich PlchotOndrej NovotnýHossein ZeinaliJohan RohdinPublished in: ICASSP (2020)
Keyphrases
- speaker identification
- speaker diarization
- speech recognition
- audio visual
- spoken language
- pattern recognition
- speech signal
- spontaneous speech
- real time
- speech synthesis
- multi lingual
- text to speech
- dialogue system
- error rate
- mobile devices
- artificial intelligence
- genetic algorithm
- information retrieval
- neural network
- data sets