Pseudo-Conventional N-Gram Representation of the Discriminative N-Gram Model for LVCSR
نویسندگان
چکیده
منابع مشابه
Discriminative n-gram language modeling
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a method based on maximizing the regularized conditional log-likelihood. The models are encoded as deterministic weighted finite state automata, and are applied by intersecting the automata with word-lattices that are t...
متن کاملDiscriminative n-gram selection for dialect recognition
Dialect recognition is a challenging and multifaceted problem. Distinguishing between dialects can rely upon many tiers of interpretation of speech data—e.g., prosodic, phonetic, spectral, and word. High-accuracy automatic methods for dialect recognition typically use either phonetic or spectral characteristics of the input. A challenge with spectral system, such as those based on shifted-delta...
متن کاملDiscriminative n-gram language modeling for Turkish
In this paper Discriminative Language Models (DLMs) are applied to the Turkish Broadcast News transcription task. Turkish presents a challenge to Automatic Speech Recognition (ASR) systems due to its rich morphology. Therefore, in addition to word n-gram features, morphology based features like root n-grams and inflectional group n-grams are incorporated into DLMs in order to improve the langua...
متن کاملDiscriminative Training of N-gram Classifi
We present a method for conditional maximum likelihood estimation of N-gram models used for text or speech utterance classification. The method employs a well known technique relying on a generalization of the Baum-Eagon inequality from polynomials to rational functions. The best performance is achieved for the 1-gram classifier where conditional maximum likelihood training reduces the class er...
متن کاملDiscriminative n - gram language modeling q
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a method based on maximizing the regularized conditional log-likelihood. The models are encoded as deterministic weighted finite state automata, and are applied by intersecting the automata with word-lattices that are t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Journal of Selected Topics in Signal Processing
سال: 2010
ISSN: 1932-4553,1941-0484
DOI: 10.1109/jstsp.2010.2047675