Distant speech processing for smart home: comparison of ASR approaches in scattered microphone network for voice command

Lecouteux, Benjamin; Vacher, Michel; Portet, François

doi:10.1007/s10772-018-9520-y

Cited by 9 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Word error rates (WER) in Table 3 show that the fMLLR and HMM-DNN models with the ESLO2 data outperform the acoustic models without it. The WER is slightly superior than a recent study using a similar approach for French voice command recognition in a smart home [35]. The NLU seq2seq model was a bi-directional LSTM en-coder and decoder.…”

Section: Pipeline Slu Baseline Approachmentioning

confidence: 90%

SLU for Voice Command in Smart Home: Comparison of Pipeline and End-to-End Approaches

Desot

Portet

Vacher

2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

Self Cite

View full text Add to dashboard Cite

HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Section: Pipeline Slu Baseline Approachmentioning

confidence: 90%

SLU for Voice Command in Smart Home: Comparison of Pipeline and End-to-End Approaches

Desot

Portet

Vacher

2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Par ailleurs, la commande vocale dans l'habitat étant résolument multicanal, le système décodait les évènements des deux canaux de plus fort RSB l'un après l'autre. Le décodage d'un canal permettait de pondérer le modèle de langage du système pour le décodage du second en employant une technique appelée Driven Decoding Algorithm (DDA) [44,45]. Ce choix a été fait suite à une étude envisageant les méthodes possibles ayant un faible coût calculatoire.…”

Section: Rap En Condition Distanteunclassified

La commande vocale en habitat intelligent : 15 ans d’expérience dans l’équipe GETALP

Vacher¹,

Portet²

2023

Revue Ouverte d'Intelligence Artificielle

Self Cite

View full text Add to dashboard Cite

getalp.imag.fr/.Résumé. -La commande vocale suscite actuellement un grand intérêt notamment dans l'habitat intelligent pour l'assistance, la santé et le confort. Depuis 2001, les travaux de l'équipe GETALP dans ce domaine s'appuient sur des allers-retours continus entre collecte de données, recherche, développements d'applications et évaluations expérimentales. Au fil des ans, entre 2001 et 2019, ces travaux ont montré la nécessité de s'attaquer aux problèmes durs de ce domaine d'application tels que l'adaptation en continu à l'utilisateur, la prise en compte de plusieurs locuteurs, la nécessité de fonctionner en ambiance bruitée et l'évaluation en milieu écologique. La démarche de l'équipe a fait usage de nombreuses expérimentations qui ont permis d'enregistrer des corpus mis à la disposition de la communauté. Les travaux et évaluations en habitat intelligent montrent la nécessité d'une approche large en considérant l'acte langagier non seulement comme une information linguistique, mais également comme une information située.Mots-clés. -Habitat intelligent, reconnaissance automatique de la parole, compréhension du langage naturel, interaction homme machine. years, since 2001 to 2019, this work has shown the need to address the hard problems of this field of application such as continuous adaptation to the user, the presence of several speakers, the need to operate in a noisy environment, and the evaluation in an ecological environment. The approach of the team uses numerous experiments that made it possible to record corpora which have been made available to the community. The current work and evaluations show the need for a broad approach by considering the language act not only as linguistic information but also as situated information.Keywords. -Smart home, automatic speech recognition, natural language understanding, Human-computer interaction.

show abstract

“…They found that the place features are most susceptible to misperceptions in white noise, followed by manner features, and then voicing features. Interactions among the IoT devices in smart homes can be executed via user interaction techniques such as human speech [12,13].…”

Section: Related Workmentioning

confidence: 99%

Development of Smart Healthcare System Based on Speech Recognition Using Support Vector Machine and Dynamic Time Warping

2020

View full text Add to dashboard Cite

This paper presents an effective solution based on speech recognition to provide elderly people, patients and disabled people with an easy control system. The goal is to build a low-cost system based on speech recognition to easily access Internet of Things (IoT) devices installed in smart homes and hospitals without relying on a centralized supervisory system. The proposed system used a Raspberry Pi board to control home appliances through wireless with smartphones. The main purpose of this system is to facilitate interactions between the user and home appliances through IoT communications based on speech commands. The proposed framework contribution uses a hybrid Support Vector Machine (SVM) with a Dynamic Time Warping (DTW) algorithm to enhance the speech recognition process. The proposed solution is a machine learning-based system for controlling smart devices through speech commands with an accuracy of 97%. The results helped patients and elderly people to access and control IoT devices that are compatible with our system using speech recognition. The proposed speech recognition system is flexible with scalability and availability in adapting to existing smart IoT devices, and it provides privacy in managing patient devices. The research provides an effective method to integrate our systems among medical institutions to help elderly people and patients. Author Contributions: Conceptualization, A.I.; Formal analysis, S.A.; Project administration, I.M.E.; Software, A.I. All authors have read and agreed to the published version of the manuscript. Conflicts of Interest:The authors declare that there is no conflict of interest.

show abstract

Distant speech processing for smart home: comparison of ASR approaches in scattered microphone network for voice command

Cited by 9 publications

References 48 publications

SLU for Voice Command in Smart Home: Comparison of Pipeline and End-to-End Approaches

SLU for Voice Command in Smart Home: Comparison of Pipeline and End-to-End Approaches

La commande vocale en habitat intelligent : 15 ans d’expérience dans l’équipe GETALP

Development of Smart Healthcare System Based on Speech Recognition Using Support Vector Machine and Dynamic Time Warping

Contact Info

Product

Resources

About