Abstract: Methods are given for improving discriminative training of hidden Markov models for continuous speech recognition. For a mixture component of a hidden Markov model state, a gradient adjustment is calculated of the standard deviation of the mixture component. If the calculated gradient adjustment is greater than a first threshold amount, an adjustment is performed of the standard deviation of the mixture component using the first threshold. If the calculated gradient adjustment is less than a second threshold amount, an adjustment is performed of the standard deviation of the mixture component using the second threshold. Otherwise, an adjustment is performed of the standard deviation of the mixture component using the calculated gradient adjustment.

Abstract: Methods are given for improving discriminative training of hidden Markov models for continuous speech recognition. For a mixture component of a hidden Markov model state, a gradient adjustment is calculated of the standard deviation of the mixture component. If the calculated gradient adjustment is greater than a first threshold amount, an adjustment is performed of the standard deviation of the mixture component using the first threshold. If the calculated gradient adjustment is less than a second threshold amount, an adjustment is performed of the standard deviation of the mixture component using the second threshold. Otherwise, an adjustment is performed of the standard deviation of the mixture component using the calculated gradient adjustment.

Abstract: Speech recognition includes use of a user profile for large vocabulary continuous speech recognition which is created without using an enrollment procedure. The user profile includes speech recognition information associated with a specific user. Large vocabulary continuous speech recognition is performed on an unknown speech input from the user utilizing the information from the user profile.

Abstract: The invention is a system and method for automatic acoustic speaker adaptation in an automatic speech recognition assisted transcription system. Partial transcripts of audio files are generated by a transcriptionist. A topic language model is generated from the partial transcripts. The topic language model is interpolated with a general language model. Automatic speech recognition is performed on the audio files by a speech recognition engine using a speaker independent acoustic model and the interpolated language model to generate semi-literal transcripts of the audio files. The semi-literal transcripts are then used with the corresponding audio files to generate a speaker dependent acoustic model in an acoustic adaptation engine.

Abstract: Methods are given for improving discriminative training of hidden Markov models for continuous speech recognition. In one approach, discriminatively trained mixture models are interpolated with maximum likelihood trained mixture models. In another approach, segmentation and recognition results from one set of models are reused to discriminatively train a second set of models. For example, segmentation and recognition results from detailed match models are mapped and used to discriminatively train fast match models. In addition, gradients for the standard deviation of mixture components are clipped based on the statistics of the gradients. Pronunciation of words may also be used to determine the “incorrect” recognition hypothesis.

Abstract: The invention is a system and method for automatic acoustic speaker adaptation in an automatic speech recognition assisted transcription system. Partial transcripts of audio files are generated by a transcriptionist. A topic language model is generated from the partial transcripts. The topic language model is interpolated with a general language model. Automatic speech recognition is performed on the audio files by a speech recognition engine using a speaker independent acoustic model and the interpolated language model to generate semi-literal transcripts of the audio files. The semi-literal transcripts are then used with the corresponding audio files to generate a speaker dependent acoustic model in an acoustic adaptation engine.

Abstract: The invention relates to a method and an apparatus for adding a new entry to a speech recognition dictionary, more particularly to a system and method for generating transcriptions from multiple utterances of a given word. The novel method and apparatus automatically transcribes several training utterances into transcriptions without knowledge of the orthography of the word being added. It also provides a method and apparatus for transcribing multiple utterances into a single transcription that can be added to a speech recognition dictionary. In a first step, each utterance is analyzed individually to get their respective acoustic characteristics. Following this, these characteristics are combined to generate a set of the most likely transcriptions using the acoustic information obtained from each of the training utterances.