Multilevel decoding for Very-Large-Size-Dictionary speech recognition

Abstract

An important concern in the field of speech recognition is the size of the vocabulary that a recognition system is able to support. Large vocabularies introduce difficulties involving the amount of computation the system must perform and the number of ambiguities it must resolve. But, for practical applications in general and for dictation tasks in particular, large vocabularies are required, because of the difficulties and inconveniences involved in restricting the speaker to the use of a limited vocabulary. This paper describes a new organization of the recognition process, Multilevel Decoding (MLD), that allows the system to support a Very-LargeSize Dictionary (VLSD)-one comprising over 100000 words. This significantly surpasses the capacity of previous speech-recognition systems. With MLD, the effect of dictionary size on the accuracy of recognition can be studied. In this paper, recognition experiments using 10000-and 200000-word dictionaries are compared. They indicate that recognition using ^Copyright 1988 by International Business Machines Corporation. Copying in printed form for private use is permitted without payment of royalty provided that (1) each reproduction is done without alteration and (2) the Journal reference and IBM copyright notice are included on the first page. The title and abstract, but no other portions, of this paper may be copied or distributed royalty free without further permission by computer-based and other information-service systems. Permission to republish any other portion of this paper must be obtained from the Editor. a 200000-word dictionary is more accurate than recognition using a 10000-word dictionary (when unrecognized words are included in the error rate).

Context dependent modeling of phones in continuous speech using decision trees

“…Both phonetic and triphone models were trained using the forward-backward algorithm in the usual manner; the triphone statistics were smoothed back onto the underlying phonetic models via deleted estimation. The topology of the triphone and and phonetic models were seven-state models with independent distributions for the beginning, middle, a.nd end of each phone as described in [12]. Results are shown in the fourth column of Table 1.…”

Statistical Testing of Segment Homogeneity in Classification of Piecewise–Regular Objects

“…To solve the ASR task, query utterance X is automatically divided into K syllables (Janakiraman et al, 2010) and the vowel segment X(k) is extracted from the k-th syllable (Pfau and Ruske, 1998). We assume that syllables are extracted without mistakes, e.g., the voice commands are produced in isolated syllable mode (Merialdo, 1988).…”

The "whiteboard" architecture

“…In gener~d, each uc~le bears a time span, a label, and a score. Grids can also be used to represent an input text obtained by scanning a bad original, or a stenotypy tape [9], and to implement some working structures (like flint of the Cocke algorithm).…”