In recent work, we proposed the rational all-pass transform (RAPT) as the basis of a speaker adaptation scheme intended for use with a large vocabulary speech recognition system. It was shown that RAPT-based adaptation reduces to a linear transformation of cepstral means, much like the better known maximum likelihood linear regression (MLLR). In a set of speech recognition experiments conducted...

Resumen En este artículo se exponen algunos de los resultados de la aplicación de las plantillas y patrones de requisitos presentadas en la edición previa del WER [6]. Uno de los resultados más interesantes de la normalización del formato de los requisitos ha sido la posibilidad de compararlos e identificar patrones de reutilización, tanto a nivel de requisitos de cliente (requisitos–C, normalm...

In this paper we present a system for automatic Arabic text diacritization using three levels of analysis granularity in a layered back off manner. We build and exploit diacritized language models (LM) for each of three different levels of granularity: surface form, morphologically segmented into prefix/stem/suffix, and character level. For each of the passes, we use Viterbi search to pick the ...

Immer schnelleres Entwickeln innovativer Produkte ist und bleibt auch in Zukunft der entscheidende Erfolgsfaktor für Unternehmen. Wer zeittreibende Konstellationen in Innovations-Projekten identifizieren kann und die entsprechenden Überwindungsstrategien zur Beschleunigung kennt und realisiert, erarbeitet sich den erstrebten Wettbewerbsvorsprung. Ontologien stellen eine Möglichkeit dar, Innovat...

This paper presents the results of the WMT16 Metrics Shared Task. We asked participants of this task to score the outputs of the MT systems involved in the WMT16 Shared Translation Task. We collected scores of 16 metrics from 9 research groups. In addition to that, we computed scores of 9 standard metrics (BLEU, SentBLEU, NIST, WER, PER, TER and CDER) as baselines. The collected scores were eva...

A coupled acousticand language-modeling approach is presented for the recognition of spontaneous speech primarily in agglutinative languages. The effectiveness of the approach in large vocabulary spontaneous speech recognition is demonstrated on the Hungarian MALACH corpus. The derivation of morphs from word forms is based on a statistical morphological segmentation tool while the mapping of mo...

In this paper, we present a concept spotting approach using manifold machine learning techniques for robust spoken language understanding. The goal of this approach is to find proper values for pre-defined slots of given meaning representation. Especially we propose a voting-based selection using multiple classifiers for robust spoken language understanding. This approach proposes no full level...

This paper compares schemes for the selection of multi-genre broadcast data and corresponding transcriptions for speech recognition model training. Selections of the same amount of data (700 hours) from lightly supervised alignments based on the same original subtitle transcripts are compared. Data segments were selected according to a maximum phone matched error rate between the lightly superv...

We describe a data collection consisting of task-oriented human-human conversations in a simulated ASR channel in which the WER is systematically varied. We find that users infrequently give a direct indication of having been misunderstood; levels of expert “initiative” increase with WER primarily due to increased grounding activity; and asking task-related questions appears to be a more succes...

The paper describes a hardware-software system for real-time closed captioning of Russian live TV broadcasts. The use of respeaking technology enabled us to create an ASR system with WER not exceeding 5.5%. Editing closed captions in real time further reduces WER down to 0.2%. In the paper we report some advancements in LMs for a highly inflected language and also in using morphological rescori...