自動化外文翻譯---改進型智能機器人的語音識別方法-資料下載頁
2025-05-11 18:41本頁面
【導讀】最近，由于其重大的理論意義和實用價值，語音識別已經(jīng)受到越來越多的關注。動態(tài)時間規(guī)整技術。隨著語音識別的深度研究，研究者發(fā)現(xiàn)，語音信號是一個復雜。最近，隨著非線性系統(tǒng)理論的發(fā)展，如人工神經(jīng)網(wǎng)絡，混沌與分形，可能應。礎上介紹了語音識別的過程。語音識別可以劃分為獨立發(fā)聲式和非獨立發(fā)聲式兩種。獨立發(fā)聲式是指其發(fā)音模式是由不同年齡，不同性別，不同地域的人來進行訓練，它能識別一個群體的指令。系統(tǒng)中，從語音信號中提取語音特征是語音識別系統(tǒng)的一個基本問題。語音識別包括訓練和識別，我們可以把它看做一種模式化的識別任務。反饋到HMM的模型參數(shù)估計中。這些參數(shù)包括意見和他們響應狀態(tài)所對應的概率密。度函數(shù)，狀態(tài)間的轉移概率，等等。輸入信號將會被確認為造成詞，其精確度是可以評估的。由于聲道共振造成的。會確認出唯一的一組預測系數(shù)。56個維數(shù)是LPCC，剩下的12個維數(shù)是分形維數(shù)。語音識別的準確性將有望改善。
【正文】 riables (CSLU, 2020). However, most ASR engineers admit that the current accuracy level for a large vocabulary unit of speech (., the sentence) remains less than 90%. Dragon39。s Naturally Speaking or IBM39。s ViaVoice, for example, show a baseline recognition accuracy of only 60% to 80%, depending upon accent, background noise, type of utterance, etc. (Ehsani amp。 Knodt, 1998). More expensive systems that are reported to outperform these two are Subarashii (Bernstein, et al., 1999), EduSpeak (Franco, et al., 2020), Phonepass (Hinks, 2020), ISLE Project (Menzel, et al., 2020) and RAD (CSLU, 2020). ASR accuracy is expected to improve. Among several types of speech recognizers used in ASR products, both implemented and proposed, the Hidden Markov Model (HMM) is one of the most dominant algorithms and has proven to be an effective method of dealing with large units of speech (Ehsani amp。 Knodt, 1998). Detailed descriptions of how the HHM model works go beyond the scope of this paper and can be found in any text concerned with language processing。 among the best are Jurafsky amp。 Martin (2020) and Hosom, Cole, and Fanty (2020). Put simply, HMM putes the probable match between the input it receives and phonemes contained in a database of hundreds of native speaker recordings (Hinks, 2020, p. 5). That is, a speech recognizer based on HMM putes how close the phonemes of a spoken input are to a corresponding model, based on probability theory. High likelihood represents good pronunciation。 low likelihood represents poor pronunciation (Larocca, et al., 1991). While ASR has been monly used for such purposes as business dictation and special needs accessibility, its market presence for language learning has increased dramatically in recent years (Aist, 1999。 Eskenazi, 1999。 Hinks, 2020). Early ASRbased software programs adopted templatebased recognition systems which perform pattern matching using dynamic programming or other time normalization techniques (Dalby amp。 KewleyPort, 1999). These programs include Talk to Me (Auralog, 1995), the Tell Me More Series (Auralog, 2020), TriplePlay Plus (Mackey amp。 Choi, 1998), New Dynamic English (DynEd, 1997), English Discoveries (Edusoft, 1998), and See it, Hear It, SAY IT! (CPI, 1997). Most of these programs do not provide any feedback on pronunciation accuracy beyond simply indicating which written dialogue choice the user has made, based on the closest pattern match. Learners are not told the accuracy of their pronunciation. In particular, Neri, et al. (2020) criticizes the graphical wave forms presented in products such as Talk to Me and Tell Me More because they look flashy to buyers, but do not give meaningful feedback to users. The 2020 version of Talk to Me has incorporated more of the features that Hinks (2020), for example, believes are useful to learners: ★ A visual signal allows learners to pare their intonation to that of the model speaker. ★ The learners39。 pronunciation accuracy is scored on a scale of seven (the higher the better). Words whose pronunciation fails to be recognized are highlighted
畢業(yè)設計相關推薦
鄂ICP備17016276號-1