Channel (broadcasting)

Speaker recognition

Pattern recognition (psychology)

Pooling

Biology

Politics

Algorithm

Political science

Speaker diarisation

Paleontology

Artificial intelligence

Management

Economics

Representation (politics)

Context (archaeology)

Word error rate

Computer science

Task (project management)

Speech recognition

Embedding

Scalability

State (computer science)

Telecommunications

Database

In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker representations. We employ 1D depth-wise separable convolutions with Squeeze-and-Excitation (SE) layers with global context followed by channel attention based statistics pooling layer to map variable-length utterances to a fixed-length embedding (t-vector). TitaNet is a scalable architecture and achieves state-of-the-art performance on speaker verification task with an equal error rate (EER) of 0.68% on the VoxCeleb1 trial file and also on speaker diarization tasks with diarization error rate (DER) of 1.73% on AMI-MixHeadset, 1.99% on AMI-Lapel and 1.11% on CH109. Furthermore, we investigate various sizes of TitaNet and present a light TitaNet-S model with only 6M parameters that achieve near state-of-the-art results in diarization tasks.

TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context