Customized Wake-Up Word with Key Word Spotting using Convolutional Neural Network

Tsai, Tsung‐Han; Hao, Ping-Cheng

doi:10.1109/isocc47750.2019.9027708

Cited by 6 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Signs with few strokes defined in this manner (less than 3) were found to have many false alarms, while those with more than 4 were prone to a high number of false rejections. This is similar to results in speech recognition, which report optimal wake word lengths of 3 to 4 syllables [72] -or, in quantitative terms, several entropy (high information-density) peaks within the continuous signal.…”

Section: A Trigger Word Detectionsupporting

confidence: 88%

ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces

Kurtoğlu¹,

Gürbüz²,

Malaia³

et al. 2021

Preprint

View full text Add to dashboard Cite

Section: A Trigger Word Detectionsupporting

confidence: 88%

ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces

Kurtoğlu¹,

Gürbüz²,

Malaia³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…Representative keywords that are spoken more frequently can be used for detecting tasks ( Abdulbaqi et al, 2020 ). Keywords can be detected for every utterance automatically using word-spotting ( Tsai and Hao, 2019 ; Gao et al, 2020 ). Identifying keywords for each task is non-trivial and requires considerable human effort.…”

Section: Task Recognition Metricsmentioning

confidence: 99%

“…This keyword was determined by calculating the most frequent words list for each task based on the premise that frequently occurring words for particular tasks can serve as features for the neural network’s task prediction. Word-spotting tools (e.g., Tsai and Hao, 2019 ; Gao et al, 2020 ) can extract keywords efficiently, reducing the reliance on traditional speech recognition. The deep learning architecture consisted of an audio network, a keyword network, and a fusion network.…”

Section: Task Recognition Algorithmsmentioning

confidence: 99%

Multi-dimensional task recognition for human-robot teaming: literature review

Baskaran,

Adams

2023

Front. Robot. AI

View full text Add to dashboard Cite

Human-robot teams collaborating to achieve tasks under various conditions, especially in unstructured, dynamic environments will require robots to adapt autonomously to a human teammate’s state. An important element of such adaptation is the robot’s ability to infer the human teammate’s tasks. Environmentally embedded sensors (e.g., motion capture and cameras) are infeasible in such environments for task recognition, but wearable sensors are a viable task recognition alternative. Human-robot teams will perform a wide variety of composite and atomic tasks, involving multiple activity components (i.e., gross motor, fine-grained motor, tactile, visual, cognitive, speech and auditory) that may occur concurrently. A robot’s ability to recognize the human’s composite, concurrent tasks is a key requirement for realizing successful teaming. Over a hundred task recognition algorithms across multiple activity components are evaluated based on six criteria: sensitivity, suitability, generalizability, composite factor, concurrency and anomaly awareness. The majority of the reviewed task recognition algorithms are not viable for human-robot teams in unstructured, dynamic environments, as they only detect tasks from a subset of activity components, incorporate non-wearable sensors, and rarely detect composite, concurrent tasks across multiple activity components.

show abstract

“…Early research studies in the field of WWS typically use audio‐only information to spot wake words [1–4, 6–9, 12–14]. In a noise‐free audio‐only environment, the performance of WWS has far exceeded the level that can be achieved by the human auditory system.…”

Section: Introductionmentioning

confidence: 99%

“…Wake Word Spotting (WWS) aims to detect pre-registered wake words by classifying utterances into a pre-defined set of words. In recent years, due to the rapid development of artificial intelligence technology, WWS [1][2][3][4] is widely used in various fields, such as mobile phone voice assistants [5][6][7][8][9], intelligent robots [10,11], and smart home devices [12][13][14][15]. For example, virtual assistants such as Microsoft's Cortana and Amazon's Alexa [16,17] rely on specific wake words for activation and further human-computer interaction.…”

Section: Introductionmentioning

confidence: 99%

On‐device audio‐visual multi‐person wake word spotting

Wang

Chen

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Audio‐visual wake word spotting is a challenging multi‐modal task that exploits visual information of lip motion patterns to supplement acoustic speech to improve overall detection performance. However, most audio‐visual wake word spotting models are only suitable for simple single‐speaker scenarios and require high computational complexity. Further development is hindered by complex multi‐person scenarios and computational limitations in mobile environments. In this paper, a novel audio‐visual model is proposed for on‐device multi‐person wake word spotting. Firstly, an attention‐based audio‐visual voice activity detection module is presented, which generates an attention score matrix of audio and visual representations to derive active speaker representation. Secondly, the knowledge distillation method is introduced to transfer knowledge from the large model to the on‐device model to control the size of our model. Moreover, a new audio‐visual dataset, PKU‐KWS, is collected for sentence‐level multi‐person wake word spotting. Experimental results on the PKU‐KWS dataset show that this approach outperforms the previous state‐of‐the‐art methods.

show abstract

Customized Wake-Up Word with Key Word Spotting using Convolutional Neural Network

Cited by 6 publications

References 2 publications

ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces

ASL Trigger Recognition in Mixed Activity/Signing Sequences for RF Sensor-Based User Interfaces

Multi-dimensional task recognition for human-robot teaming: literature review

On‐device audio‐visual multi‐person wake word spotting

Contact Info

Product

Resources

About