【正文】 llular works in many countries. Within the next few years, speech recognition will be pervasive in telephone works around the world. There are tremendous forces driving the development of the technology。 these scores are then integrated into HMMbased system architectures, in what has e to be known as hybrid systems, as described in section . An interesting feature of framebased HMM systems is that speech segments are identified during the search process, rather than explicitly. An alternate approach is to first identify speech segments, then classify the segments and use the segment scores to recognize words. This approach has produced petitive recognition performance in several tasks. 2 State of the Art Comments about the stateoftheart need to be made in the context of specific applications which reflect the constraints on the task. Moreover, different technologies are sometimes appropriate for different tasks. For example, when the vocabulary is small, the entire word can be modeled as a single unit. Such an approach is not practical for large vocabularies, where word models must be built up from subword units. The past decade has witnessed significant progress in speech recognition technology. Word error rates continue to drop by a factor of 2 every two years. Substantial progress has been made in the basic technology, leading to the lowering of barriers to speaker independence, continuous speech, and large vocabularies. There are several factors that have contributed to this rapid progress. First, there is the ing of age of the HMM. HMM is powerful in that, with the availability of training data, the parameters of the model can be trained automatically to give optimal performance. Second, much effort has gone into the development of large speech corpora for system development, training, and testing. Some of these corpora are designed for acoustic phoic research, while others are highly task specific. Nowadays, it is not unmon to have tens of thousands of sentences available for system training and testing. These corpora permit researchers to quantify the acoustic cues important for phoic contrasts and to determine parameters of the recognizers in a statistically meaningful way. While many of these corpora (., TIMIT, RM, ATIS, and WSJ。s physical and emotional state, speaking rate, or voice quality. Finally, differences in sociolinguistic background, dialect, and vocal tract size and shape can contribute to acrossspeaker variabilities. Figure shows the major ponents of a typical speech recognition system. The digitized speech signal is first transformed into a set of useful measurements or features at a fixed rate, 2 typically once every 1020 msec (see sectionsand for signal representation and digital signal processing, respectively). These measurements are then used to search for the most likely word candidate, making use of constraints imposed by the acoustic, lexical, and language models. Throughout this process, training data are used to determine the values of the model parameters. Speech recognition systems attempt to model the sources of variability described above in several ways. At the level of signal representation, researchers have developed representations that emphasize perceptually important speakerindependent features of the signal, and deemphasize speakerdependent characteristics. At the acoustic phoic level, speaker variability is typically modeled using statistical techniques applied to large amounts of data. Speaker adaptation algorithms have also been developed that adapt speakerindependent acoustic models to those of the current speaker during system use, (see section). Effects of linguistic context at the acoustic phoic level are typically handled by training separate models for phonemes in different contexts。 Technology, Portland, Oregon, USA Carnegie Mellon University, Pittsburgh, Pennsylvania, USA 1 Defining the Problem Speech recognition is the process of converting an acoustic signal, captured by a microphone or a telephone, to a set of words. The recognized words can be the final results, as for applications such as mands amp。Speech Recognition Victor Zue, Ron Cole, am