Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art
conventional models with respect to both quality, ie, word error rate (WER), and latency, ie …

Once a popular theme of futuristic science fiction or far-fetched technology forecasts, digital
home assistants with a spoken language interface have become a ubiquitous commodity …

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a
conventional speech recognition model into one neural network with a much smaller …

Language is more than words: it includes the prosodic features and patterns that we use,
subconsciously, to frame meanings and achieve our goals in our interaction with others …

There is a growing interest in the speech community in developing Recurrent Neural
Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications …

In this paper, we propose" personal VAD", a system to detect the voice activity of a target
speaker at the frame level. This system is useful for gating the inputs to a streaming on …

We present a novel keyword spotting (KWS) system that uses contextual automatic speech
recognition (ASR). For voice-activated devices, it is common that a KWS system is run on the …

Voice activity detection (VAD) is the task of predicting which parts of an utterance contains
speech versus background noise. It is an important first step to determine which samples to …

Improving the performance of end-to-end ASR models on long utterances ranging from
minutes to hours in length is an ongoing challenge in speech recognition. A common …

As speech-enabled devices such as smartphones and smart speakers become increasingly
ubiquitous, there is growing interest in building automatic speech recognition (ASR) systems …