With recent advances in speech synthesis, synthetic data is becoming a viable alternative to
real data for training speech recognition models. However, machine learning with synthetic …

We present a unified and hardware efficient architecture for two stage voice trigger detection
(VTD) and false trigger mitigation (FTM) tasks. Two stage VTD systems of voice assistants …

Always-on keyword spotting (KWS), ie, wake word detection, has been widely used in many
voice assistant applications running on smart devices. Although fixed wakeup word …

The remaining of this document is organized as follows: section 2 introduces the concept of
forced alignment, describes the framework Keyword Miner and details the use of that …

Streaming neural network models for fast frame-wise responses to various speech and
sensory signals are widely adopted on resource-constrained platforms. Hence, increasing …

Inferring a state sequence from a sequence of measurements is a fundamental problem in
bioinformatics and natural language processing. The Viterbi and the Beam Search (BS) …

Audio-only based wake word spotting (WWS) is challenging under noisy conditions due to
the environmental interference in signal transmission. In this paper, we investigate on …

Abstract End-to-end (E2E) automatic speech recognition (ASR) systems often exploited pre-
trained hidden Markov model (HMM) systems for word timing estimation (WTE), due to their …

Always-on machine learning models require a very low memory and compute footprint. Their
restricted parameter count limits the model's capacity to learn, and the effectiveness of the …

Streaming keyword spotting is a widely used solution for activating voice assistants.
Methods based on Deep Neural Networks with Hidden Markov Model (DNN-HMM) have …