Multi-Microphone Adaptive Noise Cancellation for Robust Hotword Detection

Huang, Yiteng; Shabestary, Turaj Zakizadeh; Gruenstein, Alexander; Wan, Li

doi:10.21437/interspeech.2019-3006

Cited by 14 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, the problem of detecting a speech trigger phrase is interchangeably referred to as voice trigger detection [3], keyword spotting [4], wake-up word detection [5] or hotword detection [6]. In the rest of this paper, we refer to this problem as voice trigger detection.…”

Section: Always-on Processormentioning

confidence: 99%

Multi-Task Learning for Voice Trigger Detection

Sigtia

Clark

Haynes

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We describe the design of a voice trigger detection system for smart speakers. In this study, we address two major challenges. The first is that the detectors are deployed in complex acoustic environments with external noise and loud playback by the device itself. Secondly, collecting training examples for a specific keyword or trigger phrase is challenging resulting in a scarcity of trigger phrase specific training data. We describe a two-stage cascaded architecture where a low-power detector is always running and listening for the trigger phrase. If a detection is made at this stage, the candidate audio segment is re-scored by larger, more complex models to verify that the segment contains the trigger phrase. In this study, we focus our attention on the architecture and design of these second-pass detectors. We start by training a general acoustic model that produces phonetic transcriptions given a large labelled training dataset. Next, we collect a much smaller dataset of examples that are challenging for the baseline system. We then use multi-task learning to train a model to simultaneously produce accurate phonetic transcriptions on the larger dataset and discriminate between true and easily confusable examples using the smaller dataset. Our results demonstrate that the proposed model reduces errors by half compared to the baseline in a range of challenging test conditions without requiring extra parameters.

show abstract

Section: Always-on Processormentioning

confidence: 99%

Multi-Task Learning for Voice Trigger Detection

Sigtia

Clark

Haynes

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…A recent study proposed a noise cancellation method for robust trigger detection [34]. This study used a microphone array (multi-microphone) for noise reduction and handled a single trigger word.…”

Section: Discussion On Evaluation Resultsmentioning

confidence: 99%

“…In contrast, our proposed approach targets more difficult environments in which we attempted to conduct a single microphone-based noise reduction and detect multiple trigger words simultaneously. Nevertheless, we compared the performance of our approach to that in [34]. Among several experiments that we conducted, the trigger word detection performance with noisy speech (Figure 12) could be used because this experiment was performed to investigate the trigger detection performance for a single trigger word ("alpha") for noisy speech with the proposed noise reduction method.…”

Section: Discussion On Evaluation Resultsmentioning

confidence: 99%

“…The conventional study [34] reported that the EER ranged from 10% to 20% according to microphone setting for TV noise dataset. As shown in Figure 12, our approach demonstrated similar performance when noise conditions are 5 dB and 10 dB in terms of SNR.…”

Section: Discussion On Evaluation Resultsmentioning

confidence: 99%

“…It is widely used to wake up personal assistant devices. Thus, this task is also known as wake-up-word detection or hotword detection [33,34]. Most conventional voice trigger approaches attempt to detect a single trigger word that is pertinent to the target device [31,33,35].…”

Section: Conventional Voice Triggermentioning

confidence: 99%

See 2 more Smart Citations

Front-End of Vehicle-Embedded Speech Recognition for Voice-Driven Multi-UAVs Control

Park

2020

Applied Sciences

View full text Add to dashboard Cite

For reliable speech recognition, it is necessary to handle the usage environments. In this study, we target voice-driven multi-unmanned aerial vehicles (UAVs) control. Although many studies have introduced several systems for voice-driven UAV control, most have focused on a general speech recognition architecture to control a single UAV. However, for stable voice-controlled driving, it is essential to handle the environmental conditions of UAVs carefully, including environmental noise that deteriorates recognition accuracy, and the operating scheme, e.g., how to direct a target vehicle among multiple UAVs and switch targets using speech commands. To handle these issues, we propose an efficient, vehicle-embedded speech recognition front-end for multi-UAV control via voice. First, we propose a noise reduction approach that considers non-stationary noise in outdoor environments. The proposed method improves the conventional minimum mean squared error (MMSE) approach to handle non-stationary noises, e.g., babble and vehicle noises. In addition, we propose a multi-channel voice trigger method that can control multiple UAVs while efficiently directing and switching the target vehicle via speech commands. We evaluated the proposed methods on speech corpora, and the experimental results demonstrate that the proposed methods outperform the conventional approaches. In trigger word detection experiments, our approach yielded approximately 7%, 12%, and 3% relative improvements over spectral subtraction, adaptive comb filtering, and the conventional MMSE, respectively. In addition, the proposed multi-channel voice trigger approach achieved approximately 51% relative improvement over the conventional approach based on a single trigger word.

show abstract

Deep Spoken Keyword Spotting: An Overview

López-Espejo¹,

Hansen²,

Jensen³

2022

IEEE Access

View full text Add to dashboard Cite

Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams and has become a fast-growing technology thanks to the paradigm shift introduced by deep learning a few years ago. This has allowed the rapid embedding of deep KWS in a myriad of small electronic devices with different purposes like the activation of voice assistants. Prospects suggest a sustained growth in terms of social use of this technology. Thus, it is not surprising that deep KWS has become a hot research topic among speech scientists, who constantly look for KWS performance improvement and computational complexity reduction. This context motivates this paper, in which we conduct a literature review into deep spoken KWS to assist practitioners and researchers who are interested in this technology. Specifically, this overview has a comprehensive nature by covering a thorough analysis of deep KWS systems (which includes speech features, acoustic modeling and posterior handling), robustness methods, applications, datasets, evaluation metrics, performance of deep KWS systems and audio-visual KWS. The analysis performed in this paper allows us to identify a number of directions for future research, including directions adopted from automatic speech recognition research and directions that are unique to the problem of spoken KWS.INDEX TERMS Keyword spotting, deep learning, acoustic model, small footprint, robustness.

show abstract

Multi-Microphone Adaptive Noise Cancellation for Robust Hotword Detection

Cited by 14 publications

References 14 publications

Multi-Task Learning for Voice Trigger Detection

Multi-Task Learning for Voice Trigger Detection

Front-End of Vehicle-Embedded Speech Recognition for Voice-Driven Multi-UAVs Control

Deep Spoken Keyword Spotting: An Overview

Contact Info

Product

Resources

About