Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

語用論(Pragmatics)を考える

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

http://mi.eng.cam.ac.uk/~sjy/papers/wiyo07.pdf

Partially observable Markov decision processes for spoken dialog systems

Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.

/pdf/pomdp-based-statistical-spoken-dialog-systems-a-review-52td9wfczr.pdf

POMDP-Based Statistical Spoken Dialog Systems: A Review

An image capturing device is equipped with an external parameter estimating unit for estimating external parameters using a distance image obtained by a TOF camera and a luminance image obtained by a CCD camera, a corresponding pixel determining unit for determining a correspondence relationship between pixel positions in the distance image and pixel positions in the luminance image, using previously stored internal parameters of the TOF camera and the CCD camera or the CCD camera, and the external parameters, and an occlusion searching unit for searching for an occlusion region in the distance image, using the correspondence relationship between pixel positions in the distance image and pixel positions in the luminance image.

Image capturing device, method of searching for occlusion region, and program

Correcting phoneme recognition errors in learning word pronunciation through speech interaction

We developed a multi-domain spoken dialogue system that can handle user requests across multiple domains. Such systems need to satisfy two requirements: extensibility and robustness against speech recognition errors. Extensibility is required to allow for the modification and addition of domains independent of other domains. Robustness against speech recognition errors is required because such errors are inevitable in speech recognition. However, the systems should still behave appropriately, even when their inputs are erroneous. Our system was constructed on an extensible architecture and is equipped with a robust and extensible domain selection method. Domain selection was based on three choices: (I) the previous domain, (II) the domain in which the speech recognition result can be accepted with the highest recognition score, and (III) other domains. With the third choice we newly introduced, our system can prevent dialogues from continuously being stuck in an erroneous domain. Our experimental results, obtained with 10 subjects, showed that our method reduced the domain selection errors by 18.3%, compared to a conventional method.

/pdf/multi-domain-spoken-dialogue-system-with-extensibility-and-1aykt4w0yk.pdf

Multi-Domain Spoken Dialogue System with Extensibility and Robustness against Speech Recognition Errors

PROBLEM TO BE SOLVED: To provide a dialogue system for accurately recognizing a speech to the dialogue system by using various information including information other than a voice recognition result without the necessity of a specific signal.SOLUTION: A dialogue system (100) comprises a speech detection and voice recognition unit (101) for detecting a speech and recognizing voice, and a speech feature extraction unit (103) for extracting a feature of a speech. The speech feature extraction unit determines whether an object speech is to the dialogue system on the basis of features including the length of the object speech, time relation between the object speech and a speech just before the object speech, and a system state.

Dialogue system and determination method of speech to dialogue system

This paper presents a robot audition system that recognizes simultaneous speech in the real world by using robot-embedded microphones. We have previously reported missing feature theory (MFT) based integration of sound source separation (SSS) and automatic speech recognition (ASR) for building robust robot audition. We demonstrated that a MFT-based prototype system drastically improved the performance of speech recognition even when three speakers talked to a robot simultaneously. However, the prototype system had three problems; being offline, hand-tuning of system parameters, and failure in voice activity detection (VAD). To attain online processing, we introduced FlowDesigner-based architecture to integrate sound source localization (SSL), SSS and ASR. This architecture brings fast processing and easy implementation because it provides a simple framework of shared-object-based integration. To optimize the parameters, we developed genetic algorithm (GA) based parameter optimization, because it is difficult to build an analytical optimization model for mutually dependent system parameters. To improve VAD, we integrated new VAD based on a power spectrum and location of a sound source into the system, since conventional VAD relying only on power often fails due to low signal-to-noise ratio of simultaneous speech. We, then, constructed a robot audition system for Honda ASIMO. As a result, we showed that the system worked online and fast, and had a better performance in robustness and accuracy through experiments on recognition of simultaneous speech in a noisy and echoic environment

/pdf/real-time-robot-audition-system-that-recognizes-simultaneous-2pkfigs4zf.pdf

Mikio Nakano

Papers

Image capturing device, method of searching for occlusion region, and program

Correcting phoneme recognition errors in learning word pronunciation through speech interaction

Multi-Domain Spoken Dialogue System with Extensibility and Robustness against Speech Recognition Errors

Dialogue system and determination method of speech to dialogue system

Real-Time Robot Audition System That Recognizes Simultaneous Speech in The Real World