There are various kinds of adaptation which can be used to enhance the performance of automatic speech recognizers. This paper is about pronunciation adaptation at the lexical level, i.e. about modeling pronunciation variation at the lexical level. In the early years of automatic speech recognition (ASR) research, the amount of pronunciation variation was limited by using isolated words. Since the focus gradually shifted from isolated words to conversational speech, the amount of pronunciation variation present in the speech signals has increased, as has the need to model it. This is reflected by the growing attention for this topic. In this paper, an overview of the studies on lexicon adaptation is presented. Furthermore, many examples are mentioned of situations in which lexicon adaptation is likely to improve the performance of speech recognizers. Finally, it is argued that some assumptions made in current standard ASR systems are not in line with the properties of the speech signals. Consequently, the problem of pronunciation variation at the lexical level probably cannot be solved by simply adding new transcriptions to the lexicon, as it is generally done at the moment.

In this paper we summarise the state-of-the-art for automatic speech recognition in automated Directory Assistance at the start of the 5th Framework project SMADA. Details are given about robust acoustic features for use in Distributed Speech Recognition, especially with respect to noise suppression. Then an overview is given of the confidence measures which are in use today, and their similarities and differences. Finally, work aimed at automatic update of acoustic models and automatic inference of language models is sketched that is becoming possible thanks to the very large amounts of data that can be recorded in operational services.

Speech recognition of foreign accented speech is one of the most difficult tasks in ASR. The problem of foreign accent is addressed in this study using acoustic models of the target language phonemes (French phonemes in our case) adapted with speech data from 3 other languages: English (US and UK), German and Spanish. Recognition results obtained for 11 language groups of speakers show that error rate can be significantly reduced when standard acoustic models of phonemes are adapted using speech data from other languages. Phonological rules are also introduced into the standard phonetic description of the lexical units to account for some foreign accent pronunciation variants. It appears that using phonological rules together with foreign language adapted acoustic units provides the best recognition performance. The highest error rate reduction (40%) is obtained on English speakers. 1.

This paper briefly reviews state of the art related to the topic of speech variability sources in automatic speech recognition systems. It focuses on some variations within the speech signal that make the ASR task difficult. The variations detailed in the paper are intrinsic to the speech and affect the different levels of the ASR processing chain. For different sources of speech variation, the paper summarizes the current knowledge and highlights specific feature extraction or modeling weaknesses and current trends. 1.