Related papers: Streaming keyword spotting on mobile devices

While recent zero-shot multi-speaker text-to-speech (TTS) models achieve impressive results, they typically rely on extensive transcribed speech datasets from numerous speakers and intricate training pipelines. Meanwhile, self-supervised…

When interacting with smart devices such as mobile phones or wearables, the user typically invokes a virtual assistant (VA) by saying a keyword or by pressing a button on the device. However, in many cases, the VA can accidentally be…

End-to-end (E2E) systems have achieved competitive results compared to conventional hybrid hidden Markov model (HMM)-deep neural network based automatic speech recognition (ASR) systems. Such E2E systems are attractive due to the lack of…

Modern wake word detection systems usually rely on neural networks for acoustic modeling. Transformers has recently shown superior performance over LSTM and convolutional networks in various sequence modeling tasks with their better…

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech…

The predominant use of wireless access networks is for media streaming applications, which are only gaining popularity as ever more devices become available for this purpose. However, current access networks treat all packets identically,…

Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the learning capacity of such streaming models (i.e., by adding more…

The deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. However, computational resources for these networks are significantly constrained since they usually run on-call on edge…

Using a vision-inspired keyword spotting framework, we propose an architecture with input-dependent dynamic depth capable of processing streaming audio. Specifically, we extend a conformer encoder with trainable binary gates that allow us…

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

This literature review surveys the advancements of keyword spotting (KWS) technologies, specifically focusing on Urdu, Pakistan's low-resource language (LRL), which has complex phonetics. Despite the global strides in speech technology,…

This paper explores the use of TTS synthesized training data for KWS (keyword spotting) task while minimizing development cost and time. Keyword spotting models require a huge amount of training data to be accurate, and obtaining such…

Current keyword spotting systems primarily use phoneme-level matching to distinguish confusable words but ignore user-specific pronunciation traits like prosody (intonation, stress, rhythm). This paper presents ProKWS, a novel framework…

Within the audio research community and the industry, keyword spotting (KWS) and audio tagging (AT) are seen as two distinct tasks and research fields. However, from a technical point of view, both of these tasks are identical: they predict…

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose…

The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this paper, we analyze the online operation of LAS models to…

Generative driving world models rely on compact latent state representations that must be efficiently transmitted and synchronized across distributed compute and connected vehicles. We study network-efficient streaming of a discrete world…

End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of training and indexing complexity when compared to approaches which use the output of automatic speech recognition (ASR) systems. This simplification…

This paper describes a novel method of live keyword spotting using a two-stage time delay neural network. The model is trained using transfer learning: initial training with phone targets from a large speech corpus is followed by training…

For noisy environments, ensuring the robustness of keyword spotting (KWS) systems is essential. While much research has focused on noisy KWS, less attention has been paid to multi-talker mixed speech scenarios. Unlike the usual cocktail…