Performance in speech recognition systems has progressed to the point where it is now realistic to begin integrating speech with natural language systems to produce spoken language systems. Two factors have contributed to the advances in speech: statistical modeling of the input signal and language constraints. To produce spoken language systems, then, the grammar formalisms used in natural lan...

Spoken language performance depends on both psycholinguistic processing in the individual and on communicative uses of language in dialogue or discussion. A social-communication view of language emphasizes that the spoken form of a language is used in social settings to accomplish explicit or implicit tasks of many sorts. In testing, the communicative tradition is associated with oral proficien...

The Chinese language is not only spoken by the largest population in the world, but quite different from many western languages with a very special structure. It is not alphabetic: large number of Chinese characters are ideographic symbols and pronounced as monosyllables. The open vocabulary nature, the flexible wording structure and the tone behavior are also good examples within the special s...

Progress in both speech and language processing has spurred efforts to support applications that rely on spoken—rather than written—language input. A key challenge in moving from text-based documents to such “spoken documents” is that spoken language lacks explicit punctuation and formatting, which can be crucial for good performance. This paper describes different levels of speech segmentation...

In this paper we summarize our experience at LIMSI in the design, development and evaluation of spoken language dialog systems for information retrieval tasks. This work has been for the most part carried out in the context of several European and international projects. Evaluation plays an integral role in the development of spoken language dialog systems. While there are commonly used measure...

This work introduces new methods for detecting non-scorable tests, i.e., tests that cannot be accurately scored automatically, in educational applications of spoken language proficiency assessment. Those include cases of unreliable automatic speech recognition (ASR), often because of noisy, off-topic, foreign or unintelligible speech. We examine features that estimate signalderived syllable inf...

The effect of using signed communication on the spoken language development of deaf children with a cochlear implant (CI) is much debated. We report on two studies that investigated relationships between spoken word and sign processing in children with a CI who are exposed to signs in addition to spoken language. Study 1 assessed rapid word and sign learning in 13 children with a CI and found t...

あらまし 波形素片やスペクトル素片をテンプレートとして保有し,音響照合・音声生成を行なう方法論から,HMM や GMMに代表される数理統計的な音響モデリング技術の台頭によって,音声認識・合成技術の性能・柔軟性は著し く向上した。しかし音声言語工学が構築して来た計算論的能力と,音声言語運用に関する人間の認知的能力には大き な差異があることは否めない。音声認識では,多様な話者性に対処するために数千・万の話者を使って音響モデルを 構築するが(かつ,適応技術を用いたモデル補正が必要となる),幼児の音声言語獲得過程を考えると,聴取する声 の多くは母親,父親,自身の声であり,非常に限られた話者性の音声である。音声合成に目を向ければ,合成器が生 成するのは学習話者の声である。しかし父親の太い声を模倣する幼児はいない。親の声の物真似を通して音声言語を 獲得した事例は存在しない。音声言語工学は音声言語...