Las aplicaciones de los sistemas de diálogo
Esta página ha dejado de actualizarse
Prototipo de un sistema de diálogo para acceder a información sobre los Ferrocarrils de la Generalitat (2001).
CREL, Centre de Referència en Enginyeria Lingüística de la Generalitat de Catalunya.
Consulta de la información deseada y verificación por parte del sistema.
Reconocimiento automático del habla y comprensión del habla.
Proceso de extracción de la información relevante en la consulta.
Proceso de generación de la respuesta.
Respuesta a la consulta.
Proyecto IST – Information Society Technologies (1996–1997).
BASURDE (1998–2001), Speech Interactive Research Group, Universidad del País Vasco – Grupo de Aprendizaje Computacional, Reconocimiento Automático y Traducción del Habla, Universitat Jaume I – Grupo de Tratamiento del Lenguaje Natural, Grupo de Tratamiento del Habla, Universitat Politècnica de Catalunya – Grupo de Reconocimiento de Formas e Inteligencia Artificial, Universitat Politècnica de València – Grupo de Tecnologías de las Comunicaciones, Universidad de Zaragoza.
MASK, Groupe Traitement du Langage Parlé, LIMSI Laboratoire d’Informatique pour la Mécanique et les Sciences de l’Ingénieur.
STAR, Speech Technology and Research Laboratory, SRI International.
Información sobre horarios y tarifas de vuelos.
Incluye comprensión del lenguaje natural.
PEGASUS, Spoken Language Systems Group, MIT Computer Science and Artificial Intelligence Laboratory.
Spoken Language Systems Group, MIT Computer Science and Artificial Intelligence Laboratory.
«VOYAGER can engage in verbal dialogues with users about a geographical region within Cambridge, Massachusetts, in the USA. It can provide users with information about distances, travel times, or directions between objects located within this area (e.g., restaurants, hotels, post offices, subway stops), as well as information such as addresses or telephone numbers of the objects themselves.
As of the present time, VOYAGER operates in a trilingual mode, where the user can select among the three choices, English, Japanese, or Italian, for the communication language.»
Division of Speech, Music and Hearing, KTH, Stockholm.
Información de tráfico marítimo en el archipiélago de Estocolmo.
Entrada mediante reconocimiento automático del habla.
Información proporcionada mediante síntesis del habla complementada por síntesis visual y una interfaz gráfica.
August, Division of Speech, Music and Hearing, KTH, Stockholm.
Información sobre la ciudad de Estocolmo.
Agentes conversacionales para ayudar en el proceso de obtención de información.
Grup de Tractament de la Parla, Universitat Politècnica de Catalunya – Grup de Fonètica, Universitat Autònoma de Barcelona – Servei Meteorològic de Catalunya, Generalitat de Catalunya.
Servicio dado de baja en octubre de 2011.
❯ SAM, hombre del tiempo virtual
JUPITER, Spoken Language Systems Group, MIT Computer Science and Artificial Intelligence Laboratory.
«When you call, you will be connected with Jupiter (the connection will take about 5 sec.), and the system will greet you with something like «Welcome to Jupiter – the automated weather service from MIT. How may I help you?»
At this point, you will hear a brief high pitch beep, indicating that the computer is listening. You can now ask your question, e.g., what’s the forecast in Boston, will it rain tomorrow, when will the sun rise, etc.
When you are done asking the question, you will hear a brief low pitch beep, indicating that the machine has detected an endpoint.
It will entertain you with music and then respond (hopefully with the right answer!). If it doesn’t do well, you may want to change your speaking rate a bit, or try not to trail off at the end of a sentence. You might also want to simplify your query, if you are having trouble with longer queries. The system does not do as well if you are in a noisy environment or if you use cell phones.
When it is done, then it will say «can I help you with something else» and go to step 2 again. When you are done, simply hang up.»
Grupo de Investigación en Señales, Telemática y Comunicaciones, Universidad de Granada.
Lectura del correo electrónico mediante el sistema Cotovía.
Grupo de Tecnologías Multimedia de la Universidad de Vigo y Centro Ramón Piñeiro para a Investigación en Humanidades.
Portales de voz.
Consulta de información a un portal de voz.
Proceso de consulta a un sistema con respuestas mediante plantillas previamente grabadas (Ydilo).
Forma de onda y curva melódica en un sistema con respuestas pregrabadas (Ydilo).
Proceso de consulta a un sistema con respuestas mediante conversión de texto en habla (Terra).
Comparación entre las técnicas utilizadas en dos portales de voz (Ydilo y Terra).
Voice Ticketing, Ydilo.
IVR Banca telefónica, Natural Vox.
TRAINS, Conversational Interaction and Spoken Dialogue Research Group, Rochester University.
Gestión de itinerarios de trenes.
TRIPS, Conversational Interaction and Spoken Dialogue Research Group, Rochester University.
Asistentes interactivos para la planificación.
Interacción mediante un sistema conversacional y una interfaz gráfica.
IPA, Intelligent Personal Assistant
IVA, Intelligent Virtual Assistant
PDA, Personal Digital Assistant
Respuestas correctas sobre un total de 5 000 preguntas en distintos asistentes virtuales.
Hollander, R. (2017, 27 de septiembre). Apple’s Siri ditches Bing for Google. Business insider. Consultado en http://www.businessinsider.com/apple-siri-google-bing-2017-9
Apple Inc. (2019). Siri. Consultado en https://www.apple.com/es/siri/
Gruber, T. R., Cheyer, A. J., Kittlaus, D., Guzzoni, D. R., Brigham, C. D., Giuli, R. D., … Saddler, H. J. (2011). Intelligent automated assistant (Patent number WO 2011/088053 A2). World Intellectual Property Organization, International Bureau. Geneva. Consultado en https://patentimages.storage.googleapis.com/05/08/d8/e5e538f6252621/WO2011088053A2.pdf
Siri para iPhone 4S y modelos posteriores.
Foreal. (2012, 27 de enero). Raj meets Siri | «The Big Bang Theory» The Beta Test Initiation [Documento en vídeo]. Consultado en https://www.youtube.com/watch?v=WXqRmBrBboA
Susan Bennet. Voices & Vocals. (s.f.). Consultado en https://susancbennett.com
CNET. (2013, 16 de mayo). Google Now vs. Siri: The results speak for themselves [Documento en vídeo]. Consultado en https://www.youtube.com/watch?v=z4LvJOFTlGo
Siri Team (2017). Hey Siri: An on-device DNN-powered voice trigger for Apple’s personal assistant. Apple Machine Learning Journal, 1(6). Consultado en https://machinelearning.apple.com/2017/10/01/hey-siri.html
Microsoft. (2019). Cortana. Consultado en https://www.microsoft.com/es-es/windows/cortana
Cortana
Huang, X. (2017, 20 de agosto). Microsoft researchers achieve new conversational speech recognition milestone [Entrada de blog]. Consultado en https://www.microsoft.com/en-us/research/blog/microsoft-researchers-achieve-new-conversational-speech-recognition-milestone/
Google. (s.f.). Google Assistant. Consultado el 2 de marzo de 2019, en https://assistant.google.com
Google Assistant
Artificial Solutions, Stockholm.
Indigo
Asistente personal para teléfonos inteligentes, tabletas y ordenadores de sobremesa.
Disponible en versiones en inglés para Android y Windows.
Asistente personal Indigo de Artificial Solutions.
Hello Indigo. (18/04/2013). Indigo: The ubiquitous virtual assistant for Android and WP8. Stockholm: Artificial Solutions.
Asistentes virtuales interactivos para páginas web y teléfonos móviles.
Conversión de texto en habla basada en la tecnología de Nuance - Loquendo sincronizada con movimientos labiales.
Sonia, asistente digital interactivo para teléfonos móviles.
Umanify, Barcelona.
Asistente digital interactivo para teléfonos móviles.
Umanify, Barcelona.
Asistente digital personalizado para teléfonos móviles.
Umanify, Barcelona.