The k-means clustering algorithm is an unsupervised machine learning technique that seeks to group similar data into distinct clusters, with the aim of uncovering patterns in the data that may not be apparent to the naked eye. It is possibly the most widely known algorithm for data clustering, and it…
Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism is typically based on a cross-attention module between the audio and a catalogue of biasing entries, which means computational complexity can pose severe practical limitations on the size of…
Quantization-aware training (QAT) is a leading technique for improving the accuracy of quantized neural networks. Previ- ous work has shown that decomposing training into a full-precision (FP) phase followed by a QAT phase yields superior accuracy compared to QAT alone. However, the optimal allocation of compute between the FP and…