Sound is a medium used by humans to carry information. The existence of this kind of medium is a pre-requisite for language. It is organized into a code, called speech, which provides a repertoire of forms that is shared in each language community. This code is necessary to support the linguistic interactions that allow humans to communicate. How then may a speech code be formed prior to the ex...

In this paper we describe a new testbed for developing speech recognition algorithms a VoiceMail transcription task, analogous to other tasks such as the Switchboard, CallHome, and the Hub 4 tasks, which are currently used by speech recognition researchers. We describe the collection and use of a new VoiceMail database (that is available to the research community through the LDC), and also desc...

Pronunciation variations are common sources of recognition errors in real-world applications, so that specific techniques must be developed to handle them. We are describing a method to incorporate pronunciation alternatives that have been tested with both continuous and isolated word speech recognisers for Spanish. We present an automatic grapheme-tophoneme system, modified to generate alterna...

Computer games are now a part of modern culture. By using automatic speech recognition systems (ASRS), voice driven commands can be used to control the game, which can open up the possibility for people with disabilities and age related problems to be included in game communities and use the services offered. Conventional speech recognition systems however, do not support emotions, attitudes, t...

Much effort has been expended by the speech community in designing and producing speech corpora and databases. However, considerably less thought has been given to the type of database model that best represents speech for optimal database access. This paper reviews an established database model, the relational database management system (RDBMS), as well as an emerging one, the object-oriented ...

Speech intelligibility prediction methods are popular tools within the speech processing community for objective evaluation of speech intelligibility of e.g. enhanced speech. The Short-Time Objective Intelligibility (STOI) measure has become highly used due to its simplicity and high prediction accuracy. In this paper we investigate the use of Band Importance Functions (BIFs) in the STOI measur...

The combination of multiple speech recognizers based on different signal representations is increasingly attracting interest in the speech community. In previous work we presented a hybrid speech recognition system based on the combination of acoustic and articulatory information which achieved significant word error rate reductions under highly noisy conditions on a small-vocabulary numbers re...

The standard metric to evaluate automatic speech recognition (ASR) systems is the word error rate (WER). WER has proven very useful in stand-alone ASR systems. Nowadays, these systems are often embedded in complex natural language processing systems to perform tasks like speech translation, manmachine dialogue, or information retrieval from speech. This exacerbates the need for the speech proce...

Corpus based methods are increasingly used for speech technology applications and for the development of theoretical or computer models of spoken languages. These usages range from unit selection speech synthesis to statistical modeling of speech phenomena like prosody or expressivity. In all cases, these usages require a wide range of tools for corpus creation, labeling, symbolic and acoustic ...