In a growing number of applications, such as simultaneous interpretation, audio or text may be available conveying the same information in different languages. These different views contain redundant information that can be explored to enhance the performance of speech and language processing applications. We propose a method that directly integrates ASR word graphs or lattices and phrase table...

Acoustic analysis is a proper method in vocal fold pathology diagnosis so that it can complement and in some cases replace the other invasive, based on direct vocal fold observation’s methods. There are different approaches for vocal fold pathology diagnosis. This paper presents a method based on hidden markov model which classifies speeches into two classes: the normal and the pathological. Tw...

The aim of this work is to improve the accuracy of our spoken broadcast transcription system in the task of Czech parliament speeches recognition. To achieve this goal, we propose several approaches for adaptation of both acoustic and language models of our system: a new two step unsupervised speaker adaptation strategy is presented to improve the former model while the latter one is created fr...

Word embeddings are a powerful approach for analyzing language, and exponential family embeddings (EFE) extend them to other types of data. Here we develop structured exponential family embeddings (S-EFE), a method for discovering embeddings that vary across related groups of data. We study how the word usage of U.S. Congressional speeches varies across states and party affiliation, how words a...

We present the German Sentiment Analysis Shared Task (GESTALT) which consists of two main tasks: Source, Subjective Expression and Target Extraction from Political Speeches (STEPS) and Subjective Phrase and Aspect Extraction from Product Reviews (StAR). Both tasks focused on fine-grained sentiment analysis, extracting aspects and targets with their associated subjective expressions in the Germa...

In this paper we present the ongoing work at RWTH Aachen University for building a speechto-speech translation system within the TCStar project. The corpus we work on consists of parliamentary speeches held in the European Plenary Sessions. To our knowledge, this is the first project that focuses on speech-to-speech translation applied to a real-life task. We describe the statistical approach u...