Incremental generation of word graphs
نویسندگان
چکیده
We present an algorithm for the incremental generation of word graphs. Incremental means that the speech signal is processed left-to-right by a time synchronous Viterbi algorithm and word hypotheses are generated with some delay to Viterbi decoding. The incrementally generated word hypotheses can be used for early interaction between linguistic analysis and acoustic recognition. Therefore, it is possible to derive acoustic constraints from linguistic restrictions dynamically.
منابع مشابه
Incremental Semantics Driven Natural Language Generation with Self-Repairing Capability
This paper presents the on-going development of a model of incremental semantics driven natural language generation (NLG) for incremental dialogue systems. The approach is novel in its tight integration of incremental goal-driven semantics and syntactic construction, utilizing Type Theory with Records (TTR) record types for goal concepts as its input and the grammar formalism Dynamic Syntax (DS...
متن کاملIncremental composition of static decoding graphs
A fast, scalable and memory-efficient method for static decoding graph construction is presented. As an alternative to the traditional transducer-based approach, it is based on incremental composition. Memory efficiency is achieved by combining composition, determinization and minimization into a single step, thus eliminating large intermediate graphs. We have previously reported the use of inc...
متن کاملIncremental composition of static decoding graphs with label pushing
We present new results achieved in the application of incremental graph composition algorithm, in particular using the label pushing method to further reduce the final graph size. In our previous work we have shown that the incremental composition is an efficient alternative to the conventional finite state transducer (FST) determinization-composition-minimization approach, with some limitation...
متن کاملIncremental network generation in template-based word recognition
The network representation of word templates is presented. Using the network method, words are divided into segments, and same or different word templates can share segments. This not only reduces storage required, but also enables the system to focus on acoustically dissimilar segments. Yet, by retaining multiple examples of the same word, it encapsulates variations of speech. A word recogniti...
متن کاملWord Graphs for Statistical Machine Translation
Word graphs have various applications in the field of machine translation. Therefore it is important for machine translation systems to produce compact word graphs of high quality. We will describe the generation of word graphs for state of the art phrase-based statistical machine translation. We will use these word graph to provide an analysis of the search process. We will evaluate the qualit...
متن کامل