1、语音识别系统毕业论文中英文资料对照外文翻译文献Speech Recognition Victor Zue, Ron Cole, & Wayne WardMIT Laboratory for Computer Science, Cambridge, Massachusetts, USAOregon Graduate Institute of Science & Technology, Portland, Oregon, USACarnegie Mellon University, Pittsburgh, Pennsylvania, USA 1 Defining the ProblemSpeech
2、 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 commands & control, data entry, and document preparation. They can also serve as the input to further l
3、inguistic processing in order to achieve speech understanding, a subject covered in section. Speech recognition systems can be characterized by many parameters, some of the more important of which are shown in Figure. An isolated-word speech recognition system requires that the speaker pause briefly
4、 between words, whereas a continuous speech recognition system does not. Spontaneous, or extemporaneously generated, speech contains disfluencies, and is much more difficult to recognize than speech read from script. Some systems require speaker enrollment-a user must provide samples of his or her s
5、peech before using them, whereas other systems are said to be speaker-independent, in that no enrollment is necessary. Some of the other parameters depend on the specific task. Recognition is generally more difficult when vocabularies are large or have many similar-sounding words. When speech is pro
6、duced in a sequence of words, language models or artificial grammars are used to restrict the combination of words. The simplest language model can be specified as a finite-state network, where the permissible words following each word are given explicitly. More general language models approximating
7、 natural language are specified in terms of a context-sensitive grammar. One popular measure of the difficulty of the task, combining the vocabulary size and the language model, is perplexity, loosely defined as the geometric mean of the number of words that can follow a word after the language mode
8、l has been applied (see section for a discussion of language modeling in general and perplexity in particular). Finally, there are some external parameters that can affect speech recognition system performance, including the characteristics of the environmental noise and the type and the placement o
9、f the microphone. ParametersRangeSpeaking ModeIsolated words to continuous speechSpeaking StyleRead speech to spontaneous speechEnrollmentSpeaker-dependent to Speaker-independentVocabularySmall(20,000 words)Language ModelFinite-state to context-sensitivePerplexitySmall(100)SNRHigh (30 dB) to law (10
10、dB)TransducerVoice-cancelling microphone to telephoneTable: Typical parameters used to characterize the capability of speech recognition systemsSpeech recognition is a difficult problem, largely because of the many sources of variability associated with the signal. First, the acoustic realizations o
11、f phonemes, the smallest sound units of which words are composed, are highly dependent on the context in which they appear. These phonetic variabilities are exemplified by the acoustic differences of the phoneme,At word boundaries, contextual variations can be quite dramatic-making gas shortage soun
12、d like gash shortage in American English, and devo andare sound like devandare in Italian. Second, acoustic variabilities can result from changes in the environment as well as in the position and characteristics of the transducer. Third, within-speaker variabilities can result from changes in the sp
13、eakers physical and emotional state, speaking rate, or voice quality. Finally, differences in sociolinguistic background, dialect, and vocal tract size and shape can contribute to across-speaker variabilities. Figure shows the major components of a typical speech recognition system. The digitized sp
14、eech signal is first transformed into a set of useful measurements or features at a fixed rate, typically once every 10-20 msec (see sectionsand 11.3 for signal representation and digital signal processing, respectively). These measurements are then used to search for the most likely word candidate,
15、 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. Figure: Components of a typical speech recognition system.Speech recognition systems attempt to model the sources of vari
16、ability described above in several ways. At the level of signal representation, researchers have developed representations that emphasize perceptually important speaker-independent features of the signal, and de-emphasize speaker-dependent characteristics. At the acoustic phonetic level, speaker var
17、iability is typically modeled using statistical techniques applied to large amounts of data. Speaker adaptation algorithms have also been developed that adapt speaker-independent acoustic models to those of the current speaker during system use, (see section). Effects of linguistic context at the ac
18、oustic phonetic level are typically handled by training separate models for phonemes in different contexts; this is called context dependent acoustic modeling. Word level variability can be handled by allowing alternate pronunciations of words in representations known as pronunciation networks. Comm
19、on alternate pronunciations of words, as well as effects of dialect and accent are handled by allowing search algorithms to find alternate paths of phonemes through these networks. Statistical language models, based on estimates of the frequency of occurrence of word sequences, are often used to gui
20、de the search through the most probable sequence of words. The dominant recognition paradigm in the past fifteen years is known as hidden Markov models (HMM). An HMM is a doubly stochastic model, in which the generation of the underlying phoneme string and the frame-by-frame, surface acoustic realiz
21、ations are both represented probabilistically as Markov processes, as discussed in sections,and 11.2. Neural networks have also been used to estimate the frame based scores; these scores are then integrated into HMM-based system architectures, in what has come to be known as hybrid systems, as descr
22、ibed in section 11.5. An interesting feature of frame-based 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
23、 approach has produced competitive recognition performance in several tasks.2 State of the ArtComments about the state-of-the-art need to be made in the context of specific applications which reflect the constraints on the task. Moreover, different technologies are sometimes appropriate for differen
24、t 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. Performance of speech recognition systems is typically described in terms of word erro
25、r rate E, defined as: where N is the total number of words in the test set, and S, I, and D are the total number of substitutions, insertions, and deletions, respectively. The past decade has witnessed significant progress in speech recognition technology. Word error rates continue to drop by a fact
26、or 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 coming of age of th
27、e 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
28、 are designed for acoustic phonetic research, while others are highly task specific. Nowadays, it is not uncommon to have tens of thousands of sentences available for system training and testing. These corpora permit researchers to quantify the acoustic cues important for phonetic contrasts and to d
29、etermine parameters of the recognizers in a statistically meaningful way. While many of these corpora (e.g., TIMIT, RM, ATIS, and WSJ; see section 12.3) were originally collected under the sponsorship of the U.S. Defense Advanced Research Projects Agency (ARPA) to spur human language technology deve
30、lopment among its contractors, they have nevertheless gained world-wide acceptance (e.g., in Canada, France, Germany, Japan, and the U.K.) as standards on which to evaluate speech recognition. Third, progress has been brought about by the establishment of standards for performance evaluation. Only a
31、 decade ago, researchers trained and tested their systems using locally collected data, and had not been very careful in delineating training and testing sets. As a result, it was very difficult to compare performance across systems, and a systems performance typically degraded when it was presented
32、 with previously unseen data. The recent availability of a large body of data in the public domain, coupled with the specification of evaluation standards, has resulted in uniform documentation of test results, thus contributing to greater reliability in monitoring progress (corpus development activities and evaluation methodologies are summarized in chapters 12 and 13 respectively). Finally, advances in computer technology have also indirectly influenced our progress. The availability of fast computers with inexpensive mass storage capabilities has e
copyright@ 2008-2022 冰豆网网站版权所有
经营许可证编号:鄂ICP备2022015515号-1