Search results

Recent speech synthesis systems based on sampling from autoregressive neural networks models can generate speech almost undistinguishable from human recordings. However, these models require large amounts of data. This paper shows that the lack of data from one speaker can be compensated with data from other speakers. The naturalness of Tacotron2-like models trained on a blend of 5k utterances from 7 speakers

This article presents a whisper speech detector in the far-field domain. The proposed system consists of a long short-term memory (LSTM) neural network trained on log-filterbank energy (LFBE) acoustic features. This model is trained and evaluated on recordings of human interactions with voice-controlled, far-field devices in whisper and normal phonation modes. We compare multiple inference approaches for

Building open domain conversational systems that allow users to have engaging conversations on topics of their choice is a challenging task. Alexa Prize was launched in 2016 to tackle the problem of achieving natural, sustained, coherent and engaging open-domain dialogs. In the second iteration of the competition in 2018, university teams advanced the state of the art by using context in dialog models,

Accurate prediction of conversation topics can be a valuable signal for creating coherent and engaging dialog systems. In this work, we focus on context-aware topic classification methods for identifying topics in free-form human-chatbot dialogs. We extend previous work on neural topic classification and unsupervised topic keyword detection by incorporating conversational context and dialog act features

In this paper we study techniques to improve the performance of bilinear embedding methods for knowledge graph completion on large datasets, where at each epoch the model sees a very small percentage of the training data, and the number of generated negative examples for each positive example is limited to a small portion of the entire set of entities. We first present a heuristic method to infer the types

While we have many taxonomies of forecasting methods, the authors present a classification of forecasting problems in modern industrial settings. Such a classification can help decision makers understand what resources to draw upon when facing a particular problem and may lead to more scientific discourse about the relevant data sets for benchmarking forecasting performance.

Machine Learning and NLP (Natural Language Processing) have aided the development of new and improved user experience features in many applications. We address the problem of automatically identifying the “Start Reading Location” (SRL) of eBooks, i.e. the location of the logical beginning or start of main content. This improves eBook reading experience by taking users automatically to the logical start

Recommendation systems have developed beyond simple matrix factorization to focus on two important sources of information: the temporal order of events (Hidasi et al., 2015) and side (e.g., spatial) information encoded in user and item features (Rendle, 2012). However, state-of-art temporal modeling is often limited by model capacity for long user histories. In addition, meta data are rarely used in generic

Goal-oriented dialogue systems typically rely on components specifically developed for a single task or domain. This limits such systems in two different ways: If there is an update in the task domain, the dialogue system usually needs to be updated or completely re-trained. It is also harder to extend such dialogue systems to different and multiple domains. The dialogue state tracker in conventional dialogue

We propose an alternative training framework for Bayesian neural networks (BNNs), which is motivated by viewing the Bayesian model for supervised learning as an autoencoder for data transmission. Then, a natural objective can be invoked from the rate-distortion theory. Specifically, we end up minimizing the mutual information between the weights and the dataset with a constraint that the negative log-likelihood

Intelligent personal digital assistants (IPDAs), a popular real-life application with spoken language understanding capabilities, can cover potentially thousands of overlapping domains for natural language understanding, and the task of finding the best domain to handle an utterance becomes a challenging problem on a large scale.

The current most popular method for automatic Natural Language Generation (NLG) evaluation is comparing generated text with human-written reference sentences using a metrics system, which has drawbacks around reliability and scalability. We draw inspiration from second language (L2) assessment and extract a set of linguistic features to predict human judgments of sentence naturalness. Our experiment using

The state of the art in probabilistic demand forecasting [40] minimizes Quantile Loss to predict the future demand quantiles for different horizons. However, since quantiles aren’t additive, in order to predict the total demand for any wider future interval all required intervals are usually appended to the target vector during model training. The separate optimization of these overlapping intervals can

Gunrock is a social bot designed to engage users in open domain conversations. We improved our bot iteratively using large scale user interaction data to be more capable and human-like. Our system engaged in over 40,000 conversations during the semi-finals period of the 2018 Alexa Prize. We developed a context-aware hierarchical dialog manager to handle a wide variety of user behaviors, such as topic switching

This paper describes the Tartan conversational agent built for the 2018 Alexa Prize Competition. Tartan is a non-goal-oriented socialbot focused around providing users with an engaging and fluent casual conversation. Tartan’s key features include an emphasis on structured conversation based on flexible finite-state models and an approach focused on understanding and using conversational acts. To provide

We describe IrisBot, a conversational agent that aims to help a customer be informed about the world around them, while being entertained and engaged. Our bot attempts to incorporate real-time search, informed advice, and latest news recommendation into a coherent conversation. IrisBot can already track information on the latest topics and opinions from News, Sports, and Entertainment and some specialized

In this paper we present Fantom, a social chatbot competing in the Amazon Alexa Prize 2018. The system uses a dialog graph for retrieving an approximation of the current dialog context in order to find suitable response candidates in this context. The graph is gradually built using user utterances from actual interactions, and system responses suggested by crowd workers. To this end, we developed an automatic

One of the most interesting aspects of the Amazon Alexa Prize competition is that the framing of the competition requires the development of new computational models of dialogue and its structure. Traditional computational models of dialogueare of two types: (1) task-oriented dialogue, supported by AI planning models,or simplified planning models consisting of frames with slots to be filled; or (2)search-oriented

In domain classification for spoken dialog systems, correct detection of out-of-domain (OOD) utterances is crucial because it reduces confusion and unnecessary interaction costs between users and the systems. Previous work usually utilizes OOD detectors that are trained separately from in-domain (IND) classifiers, and confidence thresholding for OOD detection given target evaluation scores. In this paper

This paper presents the second version of the dialogue system named Alquist competing in Amazon Alexa Prize 2018. We introduce a system leveraging ontology based topic structure called topic nodes. Each of the nodes consists of several sub-dialogues, and each sub-dialogue has its own LSTM-based model for dialogue management. The sub-dialogues can be triggered according to the topic hierarchy or a user intent