Update: I participated at the www.lingofest2021.com event, 2021, March 26th, presenting my talk: Enterprise Voice Cobots, where this case study is deepened. Slides and video links available at the end of the article.
Voice assistants, for consumers at home, are nowadays taken for granted, but there is a huge space of applications of voice virtual assistants also in enterprise verticals.
I want to introduce my current R&D project, involving an innovative voice assistant application in the logistics shipping container operations.
In a sentence, the voice-cobot I conceived helps forklift vehicle drivers to load and unload shipping containers from/to yard spots…
Another factor that defines a context unit of a conversation, often underrated, is the TIMING of turn-taking.
That's especially true for a real-word real-time assistant as (your) Chris navigator.
I think TIMING (mainly the human utterances time distribution) is an important attribute to be added to the list. For example if user say
The bot could reply:
Shall I call Alicia A on her mobile?
Afterward a possible user silence could be managed with a reprompt or a default choice (the mobile phone) if the user do not answer in X seconds.
Or the conversation (and the domain contect) could terminate after Y seconds of silence in the middle of a turn-taking.
What do you think about it?
As a result, Semantic Framing brings the following context units for the Chris conversations:
Thanks Duygu for the so interesting article!
Where I would read/know more about the concept of "Semanting Frames" you introduced?
Any suggestion is welcome!
BTW, that approach is very similar to what I call "dialog units" in my NaifJs opensource dialog manager:
Looking forward the context encoder architecture. A topic I thought a lot in past and I still not implemented in NaifJs.
I learned of Almond, the Stanford University open virtual assistant, for the first time one year ago reading an article on voicebot.ai.
I have been immediately enthusiastic about the core concepts on which the project is based: the user’s data privacy, the need of a web based on linguistic user interfaces, the distributed computers architecture, the natural language programming approach and many others topics related to a possible next generation of the web, populated by a federation of humans and theirs personal assistants.
Soon I discovered that one of the principal developers of Almond software is Giovanni Campagna, a PhD…
This article is a remake of my original answer to Julie Daniel Davis article Google Assistant versus Amazon Alexa: Which Could be Queen of the Classroom?
I mitigated the original title “Are Alexa and Google Assistant both looser in edutech space?”, too extreme and generic, I admit.
The reviewed article is above all a way of reflecting about my experience with CPIAbot, a chatbot I’m developing to assist no-native italian language L2/PreA1 (almost illiterate) students of some Italian public schools, as part of a ITD-CNR research project. …
In this article I want to deepen a typical problem when developing a not trivial Alexa skill, as a complex task-completion workflow or a well-structured voicefirst game: the need of a state management framework supporting developers to manage multi-turn conversations contexts.
The need of a dialog “state management” is a topic very well explained in the Chas Sweeting’s beautiful article “Lessons learned moving from web to voice development”:
My article now is a follow-up and it introduces some change request proposals for Alexa Skill Kit team about how to integrate skill state management in the Alexa Developer Portal.
7.10.2018 — added a note about X.ai
Recently I started my new job as researcher at ITD-CNR, the Institute of Educational Technology, part of the Italian National Research Council. The goal of research team to which I belong is to realize chatbots/voice assistant applications in order to support Italian language teachers that teach Italian to immigrants (both children and adults). Challenging!
We are mainly focused on voicefirst multimodal conversational apps usingsmartspeakers and smartphones and we are now experimenting the possibilities of Google Assistant (nowadays Actions On Google is the only framework that support Italian language on a smartspeaker). …
L’anno scorso, qualche mattacchione mise su youtube un video in cui veniva presentato Amazon Echo Silver, fantomatica versione e parodia del vero prodotto Amazon Echo, specificamente studiato per le persone anziane.
01–11–2018 — Warning: questo articolo compara alcune caratteristiche audio di Google Home mini e Amazon Echo Dot di seconda generazione (vedi fotografia). Dal 30 ottobre 2018 è in vendita in Italia l’Echo Dot di terza generazione, che ha caratteristiche audio completamente rinnovate rispetto al modello di precedente generazione.
24–10-2018 — Update: interessante articolo di comparazione tra Google Home mini e Amazon Echo Dot di terza generazione: Amazon’s new Echo Dot vs. the Google Home Mini: Which sounds better?
Non vi propongo il solito articolo di comparazione all'americana di un Amazon Dot e un Google Home Mini. …
Posseggo da una settimana un Google Home Mini (che in casa chiamiamo confidenzialmente “il sasso parlante”), nella versione commercializzata in Italia, ovvero in lingua italiana.
Riporto qui qualche considerazione sulle prime prove di utilizzo, un poco deludenti ma al contempo anche sorprendentemente emozionanti, ammetto, anticipando una temporanea conclusione.
Update 15 Aprile: aggiunto paragrafo su impossibilità di “ascoltare” youtube.
Update 17 Aprile: aggiunta nota su “Media responses” con le actions.
La percentuale di volte in cui Google Home “non capisce” è davvero molto alta ed i messaggi di errore sono piuttosto prolissi, ecco una lista di frasi tipiche:
Scusami, non ho…